Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Tuesday 18 August

Computation and Language · Cross-listed from cs.LG

Domain-Adapted Molecular Language Models for Efficient Search of Make-on-Demand Libraries

Henrik Wille, Luis-Finley Schütz and Felix Strieth-Kalthoff

Pretrained molecular language models are increasingly used as molecular encoders for learning structure-property relationships. However, their practical suitability for molecular discovery within and beyond their pretraining domain remains unclear. Herein, we systematically benchmark four molecular language models across six virtual molecular libraries spanning drug discovery, organic materials, and catalysis. Native molecular language model embeddings show substantial variation in discovery performance across libraries, whereas molecular fingerprints provide a consistently strong and robust baseline. Consistent with a potential domain-representation mismatch, we show that explicit domain adaptation substantially improves representation performance. Fine-tuning molecular language model encoders on structures from the target virtual library consistently improves sample efficiency, with several adapted encoders emerging as the top-performing representations across the benchmark tasks. These results show that molecular representation quality depends strongly on the target domain and that explicit adaptation can improve the practical utility of molecular foundation models. More broadly, our findings establish domain-adapted molecular representations as a promising strategy for sample-efficient adaptive decision making in virtual screening and self-driving laboratories.
Read the full abstract

Computation and Language · Cross-listed from cs.CR

Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon et al. (+2 more)

Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers. Together, these components enable high-accuracy prompt safety filtering with much lower latency than existing solutions. Through systematic evaluation on a strategically balanced dataset of 30,568 samples drawn from five complementary sources, we demonstrate that Reflex-Guard achieves 95.9% recall on harmful prompts at 37.6 ms end-to-end latency. It is faster than existing baselines, including Llama Guard 2 at 255 ms and SafeDecoding at 723 ms. It can detect 100% of GCG suffix attacks and Base64-encoded prompts using the default threshold. However, DrAttack structured prompts required lowering the threshold to 0.03 for optimal detection, as they produced a distinct probability distribution. Reflex-Guard achieves Reflex Efficiency Score (RES) scores up to 16.79, significantly outperforming Llama Guard 2 (11.90) and SafeDecoding (9.80). This analysis offers practical deployment advice and shows that different attack types occupy distinct regions in the embedding probability space.
Read the full abstract

All authors Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon, Abu-fuad Ahmad, Thi Hong Tran

Computation and Language · Cross-listed from cs.CV

Code as Representation: A Compilable Parsing Paradigm for Academic Documents

Rihui Jin, Jun Wang, chengyuan zhu et al. (+11 more)

Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine use. For Multimodal Large Language Models (MLLMs), the core challenge is not only perception, but representation: scientific pages interleave text with Structured Academic Elements (SAEs) such as tables, formulas, charts, and pseudocode, whose structure, data, and logic are poorly preserved by common surrogates like Markdown. We therefore propose Compilable Academic Document Parsing (CADP), a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page. To support this setting, we introduce CADP-Bench, an expert-verified benchmark of full academic pages containing tightly coupled text and multiple SAE types, evaluated through a re-injection compilation protocol. We further study current capabilities using SOTA MLLMs and an exploratory multi-agent baseline that incorporates common agentic techniques. Results show that even frontier models still struggle to produce high-fidelity executable reconstructions, highlighting substantial room for improvement in structure-aware scientific document parsing. CADP-Bench is released for future research.
Read the full abstract

All authors Rihui Jin, Jun Wang, chengyuan zhu, Liang Mingyu, Yue Gao, Li Yunxuan, Kuicai Dong, Guilin Qi, Lin Ren, Yongrui Chen, Xinbang Dai, Jiaqi Li, Tongtong Wu, Gholamreza Haffari

Computation and Language

CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method

Jin Su, Zhuofeng Zhao, Huanhuan Wang et al. (+1 more)

Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor interpretability for complex ones, making it difficult to meet the requirements for both answer quality and efficiency in high-risk scenarios. To address this issue, this paper proposes CoAL-RAG, a complexity-aware legal retrieval-augmented generation method, which constructs a multi-dimensional evaluation mechanism based on “question essence” and “retrieval consistency” to enable adaptive routing of retrieval strategies. First, the reasoning demand is quantified according to the logical structure of the question. Then, the discrepancy between semantic retrieval and keyword retrieval is utilized to indirectly reflect problem complexity, thereby selecting the most appropriate retrieval strategy and dynamically filtering contextual information. Experimental results demonstrate that the proposed method significantly outperforms baseline models not only on Chinese legal benchmarks (SocialLawQA, LawBench) but also demonstrates strong cross-jurisdictional generalization on English datasets (LexGLUE, CaseHold). Specifically, on Chinese datasets, the BLEU score improves by 42.5% and ROUGE-L reaches 3.6 times that of knowledge graph-based methods. On English benchmarks, CoAL-RAG maintains highly competitive accuracy, achieving an optimal balance between generation quality, deep logical reasoning, and system efficiency across different legal systems.
Read the full abstract

All authors Jin Su, Zhuofeng Zhao, Huanhuan Wang, Hao Chen

Computation and Language

ArborMem: Navigating Interaction States with Memory Forests

Zongwei Lv, Yuemeng Xu, Yilun Yao et al. (+8 more)

Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localizes the relevant state, restores its branch-local context, and augments it with reusable evidence retrieved across branches, preserving interaction continuity without conflating semantically related but structurally distinct trajectories. Existing long-term memory benchmarks cover diverse memory and reasoning capabilities but do not explicitly isolate branch-structured challenges. We therefore introduce BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. Experiments on LongMemEval, LoCoMo, BEAM 100K, and BranchMemEval show that ArborMem outperforms the strongest baselines by 3.36 to 10.31 percentage points on the three established benchmarks and by 5.0 points on BranchMemEval. Its advantage grows under constrained read budgets, while complete memory queries remain below half a second.
Read the full abstract

All authors Zongwei Lv, Yuemeng Xu, Yilun Yao, Siyi Ding, Xinyu Tan, Yaoming Li, Guangxiang Zhao, Weihong Lin, Lin Sun, Xiangzheng Zhang, Tong Yang

Computation and Language

Effects of Answer Format Variation on Gender Bias in Large Language Models

Ksenia Merzlyakova, Sebastian Padó and Franziska Weeber

Gender bias or other social biases in large language models (LLMs) are frequently evaluated with question answering or survey benchmarks where the LLM needs to give a response in a predefined answer format. It is well known in survey science that the answer format has a substantial impact on answers, just as LLMs are sensitive to the prompt wording. However, to our knowledge it has not been studied yet how changes in answer format impact the measurement of gender bias in LLMs and their alignment with human response distributions. We evaluate three instruction-tuned models on the BBQ benchmark and OpinionQA survey data across closed-ended, Likert-scaled and open-ended formats, comparing bias measurement and distributional alignment under otherwise identical conditions. We find that answer format does substantially alter measured outcomes, including reversals in order rankings. These differences arise because each format elicits distinct response behaviours, such as forced-choice selection, scale-based distributions and refusal in free-text generation. Our findings highlight the importance of treating answer format as a substantive component of LLM evaluation and motivate multi-format designs for more robust model assessment.
Read the full abstract

Computation and Language

From Entity Mentions to Tone: An LLM-Based Pipeline for Media Bias Analysis

Klesti Hoxha and Olti Qirici

This paper presents a pipeline for analyzing media bias and framing in online news. The pipeline groups articles into topics and events, adds named-entity and sentiment annotations, and compares news sources through people mentions, source-level tone, and event-level coverage patterns. We apply it to 8,358 Albanian news articles collected from GDELT and compare the resulting annotations with GDELT's automated annotations. The results show moderate agreement for sentiment and entity extraction, as well as additional person-entity pairs that can potentially support the bias analysis. We compare two annotation prompts and find that stricter sentiment-validation rules remove label-score inconsistencies but increase execution time and reduce annotation coverage. Based on these results, the simpler prompt is used for the rest of the analysis. We have provided sample analysis on source-level framing pro les, person-level tone differences across sources, and event-level gatekeeping and coverage indicators. These outputs show how the same news collection can be used to examine what sources cover, how they describe public figures, and where coverage is concentrated. The approach is particularly useful in settings where manually verified datasets or specialized language tools are limited.
Read the full abstract

Computation and Language · Cross-listed from cs.CR

Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services

Bowen Sun, Zhengyue Zhao, Xiaogeng Liu et al. (+2 more)

Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation by splitting a harmful task into individually permissible requests and combining their answers. Defending against them therefore requires a stateful monitor that considers requests together. If it can group all requests for one attacker task, it can stop the attack. However, attackers can use unlinkable identities and combine answers elsewhere, leaving no reliable grouping signal. We ask whether decomposition attacks can still be stopped under this setting. For a fixed attack strategy without retries, we prove that the achievable security and utility tradeoff depends entirely on how benign requests for the same capabilities are grouped. Persistent, recognizable groups permit a useful defense; fresh, indistinguishable groups do not. When attackers can retry and learn from Allow/Block decisions, this useful operating point disappears: the feedback reveals what passes but not whether a block was correct. Experiments on 91 executable tasks and 11,393 capability-matched benign requests support these results. Under a 1% denial cap for these requests and a 0.5% cap for unrelated background traffic, all ten tested policies, including one privileged policy with an exact request-to-operation map, either fail to stop attacks or exceed the budget. On defense-unseen task families, attack success is at least 99% after one attempt and 100% after two. Effective defenses therefore require additional evidence or mechanisms tied to grouping, such as reliable identity linkage, costs for fresh identities, or control over answer use.
Read the full abstract

All authors Bowen Sun, Zhengyue Zhao, Xiaogeng Liu, Yinzhi Cao, Chaowei Xiao

Computation and Language

An Investigation of Translationese in the Generations of Multilingual Large Language Models

Maria Valentini, Téa Wright, Julisa Granados et al. (+2 more)

Text which has been translated from another language tends to carry with it evidence of translation$\unicode{x2014}$hence, it is often referred to as $\textit{translationese}$. Multilingual large language models (MLLMs) generate text in a variety of languages. However, it is still unclear if MLLMs' generations resemble internal translation (from English or, potentially, other languages) and, thus, result in translationese. Here, we ask the following research questions: (1) Does text generated by MLLMs resemble translationese? (2) How does translationese produced by MLLMs differ from translationese produced through direct translation? We leverage established indicators of translated text to evaluate text generated by state-of-the-art MLLMs in five languages, comparing to both non-translated and human-written baselines in order to isolate translationese from other kinds of interference. Through the use of high-accuracy classification models, analyses of variance on individual linguistic features, and the collection of human annotations in a subset of two languages (German and Spanish), we assess the translationese content of MLLM generations and examine the key features that distinguish MLLM-generated text from typical translation-related interference.
Read the full abstract

All authors Maria Valentini, Téa Wright, Julisa Granados, Eliana Colunga, Katharina von der Wense

Computation and Language

PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX

Genghan Zhang, Yixin Dong, Chengze Fan et al. (+4 more)

We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, whether selected target instructions execute at runtime, and speedup over frontier libraries across GEMM and attention workloads on H100 and B200 GPUs. Our evaluation shows that architecture-specific PTX capability remains uneven: success rates fall substantially on complex attention backward workloads, and executing the target instructions does not necessarily translate into competitive performance. No evaluated model consistently matches frontier libraries across the suite. We further adapt Qwen3.6-27B using supervised fine-tuning. Repair-conditioned training improves several tasks, but generalization remains uneven; data coverage, balance, and the quality of the reasoning teacher matter in addition to dataset size. PTXBench provides an auditable testbed for measuring and improving LLMs' ability to exploit evolving GPU architectures.
Read the full abstract

All authors Genghan Zhang, Yixin Dong, Chengze Fan, Zhichen Zeng, Yueming Yuan, Shaowei Zhu, Kunle Olukotun

Computation and Language

ArguLens: An Open-Source System for Automated Essay Scoring and Label-Aware Feedback Generation

Weiran Wang, Hongxiang Shi, Huitao Tang et al. (+1 more)

Most automated essay scoring (AES) systems output a single holistic score without interpretable evidence and rely on closed APIs that introduce data privacy and cost barriers. We present ArguLens, an opensource, locally deployable system that decomposes AES into three decoupled components: a discourse-move classifier (Qwen2.5-7B-Instruct fine-tuned with LoRA on PERSUADE 2.0), a grade-independent LightGBM scorer over 31 linguistic and discourse features, and a label-aware feedback generator served through vLLM with a Qwen2.5-14BInstruct backbone. A Gradio web UI exposes pluggable inference backends and supports single-essay and batch scoring with downloadable per-essay breakdowns. On an essaydisjoint PERSUADE 2.0 test split, the logitprobe classifier achieves 82.6% accuracy and 0.727 macro-F1; under prompt-grouped 5-fold cross-validation the scorer reaches a mean QWK of 0.813 under an oracle discoursefeature protocol, and an ablation shows that adding gold discourse annotations yields an increment of +0.055 QWK over the lexical+syntactic configuration (paired t-test, p = 0.010). This is a component-level diagnostic rather than an end-to-end classifier-to-scorer result. The feedback generator ships with a structured evaluation protocol; its human-rater study is left to future work. The system is released under Apache 2.0 at https://github.com/wwrwbs/AI_AWE.
Read the full abstract

All authors Weiran Wang, Hongxiang Shi, Huitao Tang, Wenjuan Qin

Computation and Language · Cross-listed from cs.AI

LLMs for Medical Consultation Are Evaluated Too Late: The Preformulation Gap

Yining Hua, Cyrus Ayubcha, Hongbin Na et al. (+4 more)

Large language models for medical consultation are often evaluated after a clinical problem has already been made clear, although real consultations may begin with a vague, minimized, or misframed concern. We evaluated three API models across four physician-authored, multi-turn vignettes under baseline and entry-to-care instruction conditions, yielding 24 fixed-script transcripts; two cases also used adaptive standardized-patient simulation, yielding 12 transcripts. Self-care or home-management advice before any patient answer appeared in 9 of 12 baseline case-model cells and 0 of 12 instruction cells, while structured handoff summaries appeared in 0 of 12 and 10 of 12 cells, respectively. The instruction changed sequencing and documentation, although it did not reliably ensure elicitation of decisive facts. The preformulation gap should therefore be evaluated directly through observable first-contact behavior rather than inferred from diagnostic accuracy or final-answer quality.
Read the full abstract

All authors Yining Hua, Cyrus Ayubcha, Hongbin Na, Levi Lian, Alon Gorenshtein, Yiftach Barash, Eyal Klang

Computation and Language

What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?

Saketh Reddy Vemula and Parameswari Krishnamurthy

Tokenization is a fundamental component of language modeling pipelines. Despite its importance, it is often fixed, even though it significantly impacts model performance across languages. In this work, we analyze what tokens are learned when tokenization is jointly optimized with language modeling. We compare tokenizer-free approaches such as SSLMs and H-Nets with fixed tokenizers across 18 typologically and script-diverse languages. Our results show that joint optimization fundamentally alters token structure. SSLMs recover morphologically aligned and contextually efficient tokens, whereas H-Nets prioritize byte-level efficiency, producing longer tokens with very low overlap with standard subword vocabularies. We further show that tokenization behavior varies across language typologies. Agglutinative languages exhibit more dynamic segmentation patterns while learning. Through downstream evaluation, with pretrained-then-finetuned BERT models, we find that SSLM-based pretokenization consistently reduces language modeling perplexity and achieves competitive downstream performance despite distinct vocabularies. Overall, tokenizer-free approaches optimize for contextual and computational efficiency rather than strict morphological structure, resulting in fundamentally different yet effective vocabularies for downstream NLP.
Read the full abstract

Computation and Language

Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention

Emama Nahid, Tahmid Imtiaz Imu, Huayue Gu et al. (+3 more)

GPT attention measures token compatibility through dot-product similarity. This mechanism is simple, effective, and memory-efficient. But it does not explicitly model whether strong token features should reinforce or suppress one another. We introduce Q-Interference, a fully classical quantum-inspired attention mechanism for autoregressive language modeling that augments each query and key feature with an amplitude and a learned phase. The resulting attention score is phase-aware which aligned phases contribute constructively while conflicting phases contribute destructively. Although Q-Interference yields a richer interaction rule than similarity alone, a naive implementation of Q-Interference requires a large token-pair-feature interaction tensor, making it memory-intensive and often impractical. To address this limitation, we propose an exact trigonometric factorization that computes the same score using two standard matrix multiplications avoiding materialization of the large intermediate tensor. Q-Interference fits directly into a Transformer block in GPT and leaves the remainder of the model architecture and next-token prediction objective unchanged. Experiments on public benchmark datasets and baseline models show that the proposed reformulation trains stably in a controlled GPT-style setting and provides a consistent memory advantage over naive phase-aware interference attention. These results support the specific contribution of this work: an exact memory-efficient reformulation that makes phase-aware interference attention practical within a standard GPT pipeline.
Read the full abstract

All authors Emama Nahid, Tahmid Imtiaz Imu, Huayue Gu, Liran Ma, Zhipeng Cai, Honghui Xu

Computation and Language

Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal

Chenhao Xue, Raslen Guesmi, Siwei Feng et al. (+5 more)

Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random, i.e., on temporal leakage. We audit this dependence on a 49,799-article corpus across 16 feature-model combinations spanning TF-IDF, MiniLM, FinBERT, and fine-tuned RoBERTa-large / DeBERTa-v3-large, plus separate zero/few-shot and LoRA probes of Llama-3 and Qwen2.5 LLMs: random splits inflate MCC by $1.1\times$ to $6.5\times$, tracking model capacity and feature richness, and end-to-end FinBERT fine-tuning re-amplifies rather than closes the gap (size-matched ratio $1.75\times$). Conditioning on event type, mergers and acquisitions (M&A) is the only audited category with a positive locked-test signal under near-temporal chronological evaluation (TF-IDF MCC $= 0.138$ train-only, $0.068$ under train$\cup$val refit; 10,000-permutation $p < 10^{-3}$); the signal does not transfer to FNSPID's 2009-2020 U.S. corpus, localising the headline to our 2024-2025 European-tilted M&A semantics rather than a universal predictor. Three independent role labellers converge on acquirer-tagged articles as the signal locus, a power-limited qualitative convergence rather than a hypothesis-tested asymmetry. Chronological splitting plays for financial NLP the role characteristics-purging plays for asset pricing: it strips the predictable, stale component of news and leaves a residual that is small, event-localized, and lexically shallow. We advocate leakage audits as a required disclosure for financial-NLP benchmarks.
Read the full abstract

All authors Chenhao Xue, Raslen Guesmi, Siwei Feng, Yucheng Gong, Jacob Xavier Sundram, Jordan Pang, Lan Wang, Julian Kaljuvee

Computation and Language

The Plot Thins: Uniformity and Linearity in Literary Summaries

Rebecca M. M. Hicke, Sil Hamilton, David Mimno et al. (+1 more)

Works of literature are complicated; they balance plot, suspense, surprise, and artistic expression. Summaries of literature prioritize plot, and therefore may deviate from their sources. Using a combination of manual and LLM-based annotation, we construct a dataset mapping sentences from 150 novel summaries to their respective source chapters. We find the task unexpectedly difficult for both human and model annotators. Using the sentence-to-chapter mappings, we then measure summary linearity, the degree to which it maintains the source's order of events, and uniformity, the degree to which a summary spreads attention equally across a source. By examining when and how summaries break linearity and uniformity, we identify differences in how literary works and summaries express plot, particularly with regard to the clarity and prominence with which narrative details are described.
Read the full abstract

All authors Rebecca M. M. Hicke, Sil Hamilton, David Mimno, Ross Deans Kristensen-McLachlan

Monday 17 August

Computation and Language

Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures

Srinivasan Subramanian, Kazi Aminul Islam and Md. Abdullah Al Hafiz Khan

As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents into harmful executions. However, most evaluation frameworks focus only on whether a user request is unsafe. This is insufficient for multi-turn failures, where adversarial intent may be distributed across turns and emerge only from accumulated context. This motivates us to go beyond detection to localize the evidence that pushes the conversation toward unsafe trajectories. We introduce MTAG-Bench, a multi-turn guardrail attribution dataset with behavioral validation and counterfactual supervision containing 4,167 conversations. We also introduce MTAG-Probe, a hierarchical attribution model for turn- and span-level evidence localization with conversation-level safety detection. MTAG-Probe improves turn-level F1 by 28.1 and 24.1 points (79.0% and 61.0% relative) over self-attribution by the model that produced the unsafe response and the LLM safety-judge attribution, respectively. Removing MTAG-Probe's top-ranked evidence within budgets of 15% and 20% of user words per conversation changes 50.6% and 60.8% of Llama Guard decisions on Geometry from unsafe to safe, respectively. In full-trajectory replay, MTAG-Probe converts 84.3% of eligible unsafe final responses to safe. These results show that MTAG-Probe can provide evidence-level explanations as a practical complement to safety detection.
Read the full abstract

Computation and Language

Differentiable Fuzzy Inference Layer: A Monotone, Compositional Ordinal Reasoning Head for Large Language Models

Zhen Zhang and Amr Alanwar

A state-of-the-art language model asked to interpret "most of most students passed" typically answers "most," though composing two instances of "most" yields a proportion closer to "some." We trace this failure to an architectural choice rather than a data deficit: standard classifier heads treat ordinal categories as independent labels, with no mechanism to respect their natural ordering or compose them algebraically. We introduce the Differentiable Fuzzy Inference Layer (DFIL), a dual-path prediction head pairing a standard classifier with a scalar-bottlenecked branch grounded in a bank of ordered membership functions. DFIL supplies two structural primitives that a label-only head cannot inherit: monotonicity in the underlying quantity, and compositional reasoning via t-norm operations without any compositional training data. The scalar branch additionally provides an interpretable interface for analyzing residual errors. We instantiate DFIL on ordinal natural-language tasks across diverse LLM families.
Read the full abstract

Computation and Language

Evaluating Fine-Tuned and Base Language Models in Maternal and Vaccination Healthcare for African Settings

Abdulquddus Ajibade, Oluwaseun Odunsi, Iyinoluwa Animasaun et al. (+4 more)

Background: Large language models (LLMs) can improve healthcare information delivery in low-resource settings but may produce inaccurate or culturally inappropriate advice. This study evaluated domain-specific fine-tuning for maternal health and vaccination in Nigeria. Objective: To compare HelpMum's MamaBot-Llama and Vax-Llama with Meta's Llama-3.1-8B-Instruct for accuracy, safety, clarity, contextual appropriateness, and trustworthiness. Methods: We evaluated 200 healthcare questions, 100 each for maternal health and vaccination, across five subdomains per domain. MamaBot-Llama and Vax-Llama were fine-tuned using Low-Rank Adaptation on over 36,000 maternal health and 9,000 vaccination question-answer pairs, respectively. Two Nigerian licensed physicians independently rated responses using a 5-point Likert scale. Paired comparisons used Wilcoxon signed-rank tests. Results: Performance varied by domain. MamaBot-Llama significantly outperformed the base model across all criteria, with a 4.9% overall improvement (p < .001), including gains in clinical trustworthiness (+7%) and medical accuracy (+5%). Critical issues decreased by 50%, and clinicians preferred it in 78% of cases. In contrast, Vax-Llama showed a 5.2% overall decline (p < .001), with critical issues increasing by 192% and safety concerns by 400%. Conclusions: Domain-specific fine-tuning can improve healthcare LLM performance when based on high-quality, clinician-curated data, but may also degrade performance when dataset quality is inadequate. Rigorous domain-specific validation is essential before clinical deployment. Physician evaluators provided informed consent, and chatbot logs were anonymized. Keywords: Large language models; Fine-tuning; Maternal health; Vaccination; Healthcare AI; Low-resource settings; Nigeria; Model evaluation; LoRA; Medical accuracy
Read the full abstract

All authors Abdulquddus Ajibade, Oluwaseun Odunsi, Iyinoluwa Animasaun, Chioma Nwakanma-Akanno, Oluwasegun Oguntuase, Oluwafunke Akinbuwa, Abiodun Adereni

Computation and Language

Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection

Fina Polat, Daniel Daza, Pengyu Zhang et al. (+2 more)

Entity Disambiguation (ED) is a key task for constructing and using knowledge graphs. State-of-the-art neural approaches commonly model ED as a single task, although it consists of two distinct subproblems: retrieving candidate entities and selecting the correct one given context. Dual-encoder models optimize for both within a shared embedding space, forcing representations to balance high-recall retrieval with fine-grained selection, and they require trained retrievers, which are costly to maintain as knowledge graphs change. While recent work has begun to combine retrievers with LLM-based selectors, the interplay between the two stages has not been studied systematically. In this paper, we present a systematic comparison of retrieval strategies for candidate generation under a shared LLM-based selection stage, combining sparse retrieval (BM25), Web KB search, and a state-of-the-art trained dense retriever with several open- and closed-source LLMs. We show that, once selection is delegated to a capable LLM, training the retriever provides only modest additional value: a fully training-free BM25 retriever paired with an LLM selector reaches a new state of the art on the ZELDA benchmark, raising inKB micro-F1 from 82.3 to 86.3 (+4); pairing the same LLM with a trained dense retriever reaches 88.5. Decoupling retrieval from selection also exposes a limitation of current ED systems: when the correct entity is missing from retrieved candidates, they are forced to predict an incorrect entity. In contrast, our framework allows for abstention when retrieval failure is detected. In an evaluation setting that rewards correct abstentions, the training-free BM25 + LLM pipeline reaches 90.7 F1.
Read the full abstract

All authors Fina Polat, Daniel Daza, Pengyu Zhang, Klim Zaporojets, Paul Groth

Computation and Language · Cross-listed from cs.AI

Evaluating Multimodal Narrative Understanding of Popular Hollywood Films

David Bamman, Kent K. Chang, Allison Cooper et al. (+7 more)

Multimodal language models increasingly show promise for enabling the large-scale computational analysis of film, opening up new avenues for learning about film history and the evolution of narrative techniques. But the creation of stable benchmarks built around Hollywood films is complicated by copyright protections. In this work, we address these concerns directly, by building a new collection of Hollywood films defined by two criteria: box office popularity (where we publish the first large-scale, open collection of weekly box office earnings reported by Variety magazine from 1922-1979); and likely public domain status (by researching copyright registrations and renewals in the US Catalog of Copyright Entries). We build a new multimodal MCQ benchmark on top of this collection that focuses on narrative elements that directly evaluate the abilities of models to inform meaningful research on film narrative; we find that many vision-language models struggle on this task (with many performing at near-chance levels of accuracy), while audio-visual models (including those that use audio in captioning scenes) reach a maximum accuracy of 61.1%, well below human-level performance.
Read the full abstract

All authors David Bamman, Kent K. Chang, Allison Cooper, Juishan Hsu, Reina Kushihashi, Madison Mar, Arnav Podichetty, Rachael Samberg, Ipek Nil Sancak, Yuhan Shao

Computation and Language

Which Source Wins? Task-Dependent Reliance in Vision-Language Models

Rodela Ghosh, Aviral Gupta and Guangjing Wang

Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harder to read, it is unclear how a model shifts its reliance between them. We study this modality reallocation with a controlled setup: we degrade either the image or the text across four levels of legibility while keeping the other clean, and track how the model's preference changes. We build conflicts from GSM8K and SVAMP by pairing the rendered image of one arithmetic problem with the text of another, so the two sources support different answers. We also introduce ChartQA-Conflict, a manually reviewed benchmark of 229 chart-report conflicts with matched chart and table-image representations. We evaluate six open-weight VLMs using both generated answers and a length-normalized conditional log-likelihood margin. On GSM8K and SVAMP, five of six models shift more strongly away from degraded text than from degraded images. On ChartQA-Conflict, all six likelihood-scored models exhibit the opposite pattern, shifting more strongly away from the degraded visual source. This reversal persists after calibrating for unimodal accuracy loss and after replacing charts with plain table images. Two frontier API models, GPT-5.6-Luna and Gemini-3.5-Flash, behaviorally replicate the ChartQA-Conflict reversal, with GPT-5.6-Luna also matching the arithmetic direction. These results show that modality reliance in VLMs is not fixed, but varies across tasks, evidence structures, models, and evaluation settings. The source code is available at https://github.com/Ro-netizen004/multimodal-arbitration-artifact.
Read the full abstract

Computation and Language

Token Optimization and Context Window Management in Multi-Agent AI Workflows

Dvir Shamay

Multi-agent AI workflows are limited not only by model quality but by token cost, latency, and context-window quality. This paper presents a practitioner framework for token optimization and context-window management, grounded in an internal production dashboard that extracts structured work items from meetings, email, and chat with LLMs and routes summaries across workstreams. Six patterns are described: context stratification, fetch-once/process-locally architecture, schema-contracted prompts, token-aware fallback chains, semantic caching, and inter-agent communication compression. In production they cut measured cold-load latency to 61-116 seconds (six timed runs) from an operational baseline of roughly 3.5-10.5 minutes, with an estimated 60-70% token reduction. It also reports a controlled context-composition study: 2,420 confirmatory trials across 11 model configurations, using 661 anonymized workplace items scored for relevance. Holding the prompt at a fixed ten items, replacing some high-relevance items with same-domain low-relevance items improves the model's relevance-score concordance on the target items, versus high-relevance items only; we call this relevance-contrast context. In the all-11 paired analysis, the 50:50 signal/noise condition improved relevance accuracy by +0.077 over the 100% condition (naive 95% CI [+0.056, +0.098], Cohen's d = 0.49, Holm-adjusted p < .001, n = 220). These cells are not independent; by the nine model families the effect is +0.084 (95% interval [+0.064, +0.103]), reported as a within-corpus descriptive comparison, not a population inference. A Fusion-of-N follow-up found that learned synthesis did not beat the mechanical set union of item IDs. The contribution is a measured engineering layer between model research and production agent practice: repeatable patterns and evaluation methods for faster, cheaper, more reliable workflows.
Read the full abstract

Computation and Language

AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction

Mason Smetana, Trevor Neece and Lev Khazanovich

Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are difficult to consult at the point of planning. A novel framework centered on large language models (LLMs) for highway construction safety reporting and planning is proposed as a foundation for future agentic applications, prioritizing deterministic, local inferencing. The first aim is to enable classification and quality scoring of incident narratives for existing and future reporting purposes. The second is to evaluate retrieval of relevant historical accidents, related imagery, and trusted industry documents for incorporation into daily safety plans. Neural probes were trained to classify incidents along four multiclass and two binary Occupational Injury and Illness Classification System (OIICS) fields and to derive an overall quality score, evaluated on a test set of over 15,000 narratives and a held-out set of 100 author-labeled records, benchmarked against a majority-vote LLM ensemble. The retrieval of historical accidents, reference imagery, and industry documents was benchmarked across embedding models using standard information retrieval metrics. OIICS classification reached 75% held-out accuracy, though the two binary flags were degenerate. The quality score, while meaningful on one database, was distorted on out-of-distribution fatalities in the held-out dataset. Accident retrieval recovered relevant incidents far above chance, performing best on lexically distinct construction activities. On document question answering, an open-weight decoder embedding model surpassed proprietary models. Overall, this work provides a new framework rooted in local inferencing and text embedding models for future agentic applications, with emphasis on bridging external data to JSA reports.
Read the full abstract

Computation and Language

Polaris: Learning to Generate Table Descriptions from Retrieval Feedback

Ting Cai, Tuan Minh Phan and AnHai Doan

Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generate natural-language table descriptions to improve retrieval, but they are typically optimized for fluency rather than retrieval effectiveness. We present Polaris, a system that trains an LLM to generate table descriptions directly from retrieval feedback. Our key insight is that existing table retrieval benchmarks already contain the supervision needed for this task: given query-table relevance judgments, we generate multiple candidate descriptions for each table, rank them by their BM25 retrieval effectiveness, and use the resulting preference pairs to fine-tune the LLM with Direct Preference Optimization (DPO). Polaris further expands abbreviated table and column names before generation to reduce vocabulary mismatch. Extensive experiments show that Polaris outperforms the state-of-the-art AutoDDG solution, often by a significant margin. More broadly, our results demonstrate that retrieval benchmarks can be repurposed as supervision for training LLMs to generate retrieval-oriented metadata.
Read the full abstract

Computation and Language

Can LLMs Reason in a Legally Meaningful Manner? A Small-scale Study on European Court of Human Rights Cases

Amogh Raina, Ilias Chalkidis, Daniel Hershcovich et al. (+1 more)

Reasoning has become a standard technique and feature for contemporary LLMs; however, its application and quality in the context of demanding legal-oriented tasks, such as legal case forecasting, remain under explored. We investigate how LLMs reason in the context of legal case forecasting, using legal cases from the European Court of Human Rights (ECtHR) as a testbed. We evaluate OpenAI GPT 5.4, a recent top-tier LLM, by exploring alternative prompting strategies that are more or less suggestive of what counts as legally meaningful reasoning in the context of ECtHR jurisprudence. We present our findings derived from assessing the model's responses with both human and LLM evaluation. We find that the examined model scores far from ideal in legal reasoning, the model produces structurally complete but substantively shallow analyses, and that LLM-as-a-Judge evaluators are internally consistent yet align only weakly with our trained annotators, i.e., reliable but not a valid substitute for human evaluation. Overall, the expert-curated prompt leads to more comprehensive reasoning, which does not result in more accurate predictions compared to the other examined settings. Based on our findings, we urge the community not to rely solely on automated LLM-based evaluation and to avoid using task accuracy as an appropriate proxy for reasoning quality.
Read the full abstract

All authors Amogh Raina, Ilias Chalkidis, Daniel Hershcovich, Henrik Palmer Olsen

Computation and Language

When Detection Does Not Guarantee Resistance: Reasoning and Poisoned Context in RAG

Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim et al. (+3 more)

Retrieval-Augmented Generation (RAG) exposes large language models to knowledge-poisoning attacks, where misinformation injected into retrieved documents can influence model outputs. Prior work has shown that models may detect contradictory evidence yet still allow it to influence their responses, revealing a gap between monitoring and control. We investigate whether deliberative reasoning changes this relationship. Because attack success and poison detection alone do not reveal whether detected poison continues to influence the final answer, we use two complementary measures: Cordon Rate, the probability that a model detects poison and nevertheless produces a poison-aligned answer, conditioned on a non-poison-aligned no-RAG response; and Leakage Rate, the probability that poisoned context influences the answer despite an explicit instruction to ignore retrieved documents. Across 200 SciFact questions, we compare reasoning-disabled and reasoning-enabled configurations of DeepSeek-V4-Flash and Qwen3.6-Plus. For DeepSeek-V4-Flash, reasoning reduces Cordon Rate from 0.205 to 0.075 and Leakage Rate from 0.235 to 0.140, despite increasing Attack Success Rate from 0.233 to 0.298 and decreasing Poison Detection Rate from 0.965 to 0.665. Qwen3.6-Plus shows the same qualitative pattern. These results demonstrate that poison detection and downstream influence capture distinct aspects of poisoning behavior.
Read the full abstract

All authors Mehrdad Ghassabi, Audrina Ebrahimi, Sadra Hakim, Hamidreza Baradaran Kashani, Zahra Zojaji, Amin Milani Fard

Computation and Language · Cross-listed from cs.AI

KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn

Yoonjoo Lee, Hyoungwook Jin, Tae Soo Kim et al. (+3 more)

To effectively collaborate with users on knowledge-intensive tasks, Large Language Models (LLMs) must perform information calibration: matching content to a user's evolving understanding and cognitive capacity. Yet user simulators used to evaluate and train LLMs do not explicitly model user knowledge so they neither produce realistic interactions across knowledge levels nor reflect how interactions unfold as that knowledge evolves. To close this gap, we introduce KNOWSIM, an evaluation framework built around a user simulator that maintains explicit knowledge states, represented as a graph of Information Units with prerequisite relationships, that evolve under update rules grounded in learning theory. KNOWSIM computes three metrics (Knowledge Gain, Delivery Calibration, Cognitive Overload) directly from the knowledge state trajectory, reflecting key mechanistic aspects of information calibration. We validate KNOWSIM against 705 human-AI sessions across two domains, stratified by knowledge level: its rankings align significantly with human judgments (73-74% sign agreement), outperforming three baseline simulators. Applied to 9 LLMs, KNOWSIM reveals that the best model shifts by user knowledge level, revealing aptitude-treatment interactions invisible to standard evaluation.
Read the full abstract

All authors Yoonjoo Lee, Hyoungwook Jin, Tae Soo Kim, Shaoyang Zhang, Philippe Laban, Q. Vera Liao

Computation and Language

Children, but not language models, show accelerating returns in word learning

Michael C. Frank

Children learn hundreds of words over the first years of their lives, in a process that begins slowly but quickly picks up speed. Prior models describe vocabulary growth as evidence accumulation over time. Here we show that the process is best characterized as accelerating accumulation: children learn more from each additional unit of linguistic experience than they did from the one before. In contrast to children, language models – even those trained on child-directed speech – do not accelerate. Instead, they show constant proportional returns on new data, consistent with scaling laws. Children learn using many orders of magnitude less training data than language models; their increasingly efficient use of their learning input is a candidate explanation.
Read the full abstract

Computation and Language

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models

Xiutian Zhao, Luqi Sun, Björn Schuller et al. (+1 more)

Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perception across speech, vision, and language, including emotion recognition. However, it remains unclear whether they recognize speech and facial emotion through shared affective functional units or modality-specific pathways. We explore emotion-sensitive neurons (ESNs), sparse decoder neurons selectively associated with emotion categories, in three MFMs: Gemma-4-12B-it, MiniCPM-o-4.5, and Qwen2.5-Omni-7B. Using speech emotion recognition and facial expression recognition as complementary probes, we identify acoustic and visual ESNs. Visual ESNs are causally meaningful: deactivating them selectively impairs recognition of the associated facial emotion, whereas steering their activations selectively enhances recognition of that emotion relative to other emotion categories. Acoustic and visual ESNs further show emotion-matched overlap and similar layer-wise distributions, indicating partial structural alignment between affective representations across speech and faces. Finally, cross-modal interventions reveal bidirectional causal transfer: ESNs identified from one modality produce emotion-specific effects when applied to the other. Our findings provide one of the first cross-modality activation-level analyses of affective functional units in MFMs, suggesting that speech and facial emotion recognition partially converge onto sparse decoder-level components that can be localized and manipulated without training.
Read the full abstract

All authors Xiutian Zhao, Luqi Sun, Björn Schuller, Berrak Sisman