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

Wednesday 11 March

Computation and Language

PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses

Minki Hong, Eunsoo Lee, Sohyun Park et al. (+1 more)

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses. PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, coherence, relevance, objectivity, clarity, conciseness), and uses an LLM-based evaluator to output (i) scalar scores on a 1-5 Likert scale and (ii) criterion-specific natural-language rationales grounded in the rubric. Across 7 benchmarks and 5 task models, PEEM's accuracy axis strongly aligns with conventional accuracy while preserving model rankings (aggregate Spearman rho about 0.97, Pearson r about 0.94, p < 0.001). A multi-evaluator study with four models shows consistent relative judgments (pairwise rho = 0.68-0.85), supporting evaluator-agnostic deployment. Beyond alignment, PEEM captures complementary linguistic failure modes and remains informative under prompt perturbations: prompt-quality trends track downstream accuracy under iterative rewrites, semantic adversarial manipulations induce clear score degradation, and meaning-preserving paraphrases yield high stability (robustness rate about 76.7-80.6%). Finally, using only PEEM scores and rationales as feedback, a zero-shot prompt rewriting loop improves downstream accuracy by up to 11.7 points, outperforming supervised and RL-based prompt-optimization baselines. Overall, PEEM provides a reproducible, criterion-driven protocol that links prompt formulation to response behavior and enables systematic diagnosis and optimization of LLM interactions.
Read the full abstract

All authors Minki Hong, Eunsoo Lee, Sohyun Park, Jihie Kim

Computation and Language

Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs

Panatchakorn Anantaprayoon, Nataliia Babina, Nima Asgharbeygi et al. (+1 more)

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However, these approaches remain limited in multi-stakeholder settings, where conflicting values arise and deliberative negotiation is required. This work proposes a multi-agent negotiation-based alignment framework that aligns LLMs to Collective Agency (CA)-an existing alignment objective introduced to promote the continual expansion of agency-while simultaneously improving conflict-resolution capability. To enable scalable training, two self-play LLM instances are assigned opposing personas and engage in turn-based dialogue to synthesize mutually beneficial solutions. We generate synthetic moral-dilemma prompts and conflicting persona pairs, and optimize the policy via RLAIF using Group Relative Policy Optimization (GRPO) with an external LLM reward model. While rewards are computed from CA scores assigned to the final completion, gradients are applied to dialogue tokens to directly improve deliberative interaction dynamics. Experiments show that the model achieves CA alignment comparable to a single-agent baseline while substantially improving conflict-resolution performance without degrading general language capabilities. These results suggest that negotiation-driven deliberation training provides a practical path toward LLMs that better support collective decision-making in value-conflict scenarios.
Read the full abstract

All authors Panatchakorn Anantaprayoon, Nataliia Babina, Nima Asgharbeygi, Jad Tarifi

Computation and Language

Aligning Large Language Models with Searcher Preferences

Wei Wu, Peilun Zhou, Liyi Chen et al. (+6 more)

The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and deployment of open-ended generative search on large content platforms remain limited. This setting introduces challenges, including robustness to noisy retrieval, non-negotiable safety guarantees, and alignment with diverse user needs. In this work, we introduce SearchLLM, the first large language model (LLM) for open-ended generative search. We design a hierarchical, multi-dimensional reward system that separates bottom-line constraints, including factual grounding, basic answer quality and format compliance, from behavior optimization objectives that promote robustness to noisy retrieval and alignment with user needs. Concretely, our reward model evaluates responses conditioned on the user query, session history, and retrieved evidence set, combining rule-based checks with human-calibrated LLM judges to produce an interpretable score vector over these dimensions. We introduce a Gated Aggregation Strategy to derive the training reward for optimizing SearchLLM with Group Relative Policy Optimization (GRPO). We deploy SearchLLM in the AI search entry of RedNote. Offline evaluations and online A/B tests show improved generation quality and user engagement, increasing Valid Consumption Rate by 1.03% and reducing Re-search Rate by 2.81%, while upholding strict safety and reliability standards.
Read the full abstract

All authors Wei Wu, Peilun Zhou, Liyi Chen, Qimeng Wang, Chengqiang Lu, Yan Gao, Yi Wu, Yao Hu, Hui Xiong

Computation and Language · Cross-listed from eess.AS

Speech Codec Probing from Semantic and Phonetic Perspectives

Xuan Shi, Chang Zeng, Tiantian Feng et al. (+3 more)

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term "semantic" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through three tasks. Our results show that current tokenizers primarily capture phonetic rather than lexical-semantic structure, deriving practical implications for the design of next-generation speech tokenization methods. Code is released to public at https://github.com/Alexuan/codec_probing_release.
Read the full abstract

All authors Xuan Shi, Chang Zeng, Tiantian Feng, Shih-Heng Wang, Jianbo Ma, Shrikanth Narayanan

Computation and Language

Dynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking

Haoxiang Su, Ruiyu Fang, Liting Jiang et al. (+2 more)

The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions. However, current multi-domain DST encounters two key challenges: the difficulty of effectively modeling dialogue history and the limited availability of annotated data, both of which hinder model performance. To tackle the aforementioned problems, we develop a dynamic knowledge fusion framework applicable to multi-domain DST. The model operates in two stages: first, an encoder-only network trained with contrastive learning encodes dialogue history and candidate slots, selecting relevant slots based on correlation scores; second, dynamic knowledge fusion leverages the structured information of selected slots as contextual prompts to enhance the accuracy and consistency of dialogue state tracking. This design enables more accurate integration of dialogue context and domain knowledge. Results obtained from multi-domain dialogue benchmarks indicate that our method notably improves both tracking accuracy and generalization, validating its capability in handling complex dialogue scenarios.
Read the full abstract

All authors Haoxiang Su, Ruiyu Fang, Liting Jiang, Xiaomeng Huang, Shuangyong Song

Computation and Language

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck

Hongbin Zhang, Kehai Chen, Xuefen Bai et al. (+4 more)

Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is characterized as LLMs systematically favoring machine-translated text over human-authored references, particularly in low-resource languages. We attribute this bias to spurious correlations with (i) latent manifold alignment with English and (ii) cross-lingual predictability. To mitigate this bias, we propose DIBJudge, a robust fine-tuning framework that learns a minimally sufficient, judgment-critical representation via variational information compression, while explicitly isolating spurious factors into the dedicated bias branch. Furthermore, we incorporate a cross-covariance penalty that explicitly suppresses statistical dependence between robust and bias representations, thereby encouraging effective disentanglement. Extensive evaluations on multilingual reward modeling benchmarks and a dedicated translationese bias evaluation suite demonstrate that the proposed DIBJudge consistently outperforms strong baselines and substantially mitigates translationese bias.
Read the full abstract

All authors Hongbin Zhang, Kehai Chen, Xuefen Bai, Youcheng Pan, Yang Xiang, Jinpeng Wang, Min Zhang

Computation and Language

Large language models can disambiguate opioid slang on social media

Kristy A. Carpenter, Issah A. Samori, Mathew V. Kiang et al. (+4 more)

Social media text shows promise for monitoring trends in the opioid overdose crisis; however, the overwhelming majority of social media text is unrelated to opioids. When leveraging social media text to monitor trends in the ongoing opioid overdose crisis, a common strategy for identifying relevant content is to use a lexicon of opioid-related terms as inclusion criteria. However, many slang terms for opioids, such as "smack" or "blues," have common non-opioid meanings, making them ambiguous. The advanced textual reasoning capability of large language models (LLMs) presents an opportunity to disambiguate these slang terms at scale. We present three tasks on which to evaluate four state-of-the-art LLMs (GPT-4, GPT-5, Gemini 2.5 Pro, and Claude Sonnet 4.5): a lexicon-based setting, in which the LLM must disambiguate a specific term within the context of a given post; a lexicon-free setting, in which the LLM must identify opioid-related posts from context without a lexicon; and an emergent slang setting, in which the LLM must identify opioid-related posts with simulated new slang terms. All four LLMs showed excellent performance across all tasks. In both subtasks of the lexicon-based setting, LLM F1 scores ("fenty" subtask: 0.824-0.972; "smack" subtask: 0.540-0.862) far exceeded those of the best lexicon strategy (0.126 and 0.009, respectively). In the lexicon-free task, LLM F1 scores (0.544-0.769) surpassed those of lexicons (0.080-0.540), and LLMs demonstrated uniformly higher recall. On emergent slang, all LLMs had higher accuracy (average: 0.784), F1 score (average: 0.712), precision (average: 0.981), and recall (average: 0.587) than the two lexicons assessed. Our results show that LLMs can be used to identify relevant content for low-prevalence topics, including but not limited to opioid references, enhancing data provided to downstream analyses and predictive models.
Read the full abstract

All authors Kristy A. Carpenter, Issah A. Samori, Mathew V. Kiang, Keith Humphreys, Anna Lembke, Johannes C. Eichstaedt, Russ B. Altman

Computation and Language

Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

Tim Schopf and Michael Färber

Judging the novelty of research ideas is crucial for advancing science, enabling the identification of unexplored directions, and ensuring contributions meaningfully extend existing knowledge rather than reiterate minor variations. However, given the exponential growth of scientific literature, manually judging the novelty of research ideas through literature reviews is labor-intensive, subjective, and infeasible at scale. Therefore, recent efforts have proposed automated approaches for research idea novelty judgment. Yet, evaluation of these approaches remains largely inconsistent and is typically based on non-standardized human evaluations, hindering large-scale, comparable evaluations. To address this, we introduce RINoBench, the first comprehensive benchmark for large-scale evaluation of research idea novelty judgments. It comprises 1,381 research ideas derived from and judged by human experts as well as nine automated evaluation metrics designed to assess both rubric-based novelty scores and textual justifications of novelty judgments. Using this benchmark, we evaluate several state-of-the-art large language models (LLMs) on their ability to judge the novelty of research ideas. Our findings reveal that while LLM-generated reasoning closely mirrors human rationales, this alignment does not reliably translate into accurate novelty judgments, which diverge significantly from human gold standard judgments - even among leading reasoning-capable models. Data and code available at: https://github.com/TimSchopf/RINoBench.
Read the full abstract

Tuesday 10 March

Computation and Language · Cross-listed from cs.CY

Classifying Problem and Solution Framing in Congressional Social Media

Misha Melnyk, Mitchell Dolny, Joshua D. Elkind et al. (+6 more)

Policy setting in the USA according to the “Garbage Can” model differentiates between “problem” and “solution” focused processes. In this paper, we study a large dataset of US Senator postings on Twitter (1.68m tweets in total). Our objective is to develop an automated method to label Senatorial posts as either in the problem or solution streams. Two academic policy experts labeled a subset of 3967 tweets as either problem, solution, or other (anything not problem or solution). We split off a subset of 500 tweets into a test set, with the remaining 3467 used for training. During development, this training set was further split by 60/20/20 proportions for fitting, validation, and development test sets. We investigated supervised learning methods for building problem/solution classifiers directly on the training set, evaluating their performance in terms of F1 score on the validation set, allowing us to rapidly iterate through models and hyperparameters, achieving an average weighted F1 score of above 0.8 on cross validation across the three categories using a BERTweet Base model.
Read the full abstract

All authors Misha Melnyk, Mitchell Dolny, Joshua D. Elkind, A. Michael Tjhin, Saisha Chebium, Blake VanBerlo, Annelise Russell, Michelle M. Buehlmann, Jesse Hoey

Computation and Language

Think Twice Before You Write – an Entropy-based Decoding Strategy to Enhance LLM Reasoning

Jiashu He, Meizhu Liu, Olaitan P Olaleye et al. (+9 more)

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches introduce randomness without adequate robustness. Self-consistency improves reliability by aggregating multiple rollouts, but incurs significant computational overhead. We propose an entropy-guided decoding framework that introduces token-level adaptivity into generation. At each step, the model computes the entropy of the token distribution, identifies high-uncertainty positions, and selectively branches on these vulnerable points. A dynamic pool of partial rollouts is maintained and expanded until solutions are completed, concentrating computation where uncertainty is greatest and avoiding unnecessary exploration in confident regions. To enable efficient termination, we apply a rollout-level Entropy After </Think> (EAT) stopping criterion by performing entropy evaluation after the full reasoning trace, rather than incrementally at every step. Experiments on GSM8K, AMC2023, and their perturbed variants demonstrate that our method achieves consistently strong accuracy. Notably, on smaller LLMs, performance is comparable to GPT-5 while operating at a fraction of the cost.
Read the full abstract

All authors Jiashu He, Meizhu Liu, Olaitan P Olaleye, Amit Agarwal, M. Avendi, Yassi Abbasi, Matthew Rowe, Hitesh Laxmichand Patel, Paul Li, Tao Sheng, Sujith Ravi, Dan Roth

Computation and Language

Semantic Shifts of Psychological Concepts in Scientific and Popular Media Discourse: A Distributional Semantics Analysis of Russian-Language Corpora

Orlova Anastasia

This article examines semantic shifts in psychological concepts across scientific and popular media discourse using methods of distributional semantics applied to Russian-language corpora. Two corpora were compiled: a scientific corpus of approximately 300 research articles from the journals Psychology. Journal of the Higher School of Economics and Vestnik of Saint Petersburg University. Psychology (767,543 tokens) and a popular science corpus consisting of texts from the online psychology platforms Yasno and Chistye kogntsii (1,199,150 tokens). After preprocessing (OCR recognition, lemmatization, removal of stop words and non-informative characters), the corpora were analyzed through frequency analysis, clustering, and the identification of semantic associations. The results reveal significant differences in vocabulary and conceptual framing between the two discourse types: scientific texts emphasize methodological and clinical terminology, while popular science materials foreground everyday experience and therapeutic practice. A comparison of semantic associations for key concepts such as burnout and depression shows that scientific discourse links these terms to psychological resources, symptomatology, and diagnostic constructs, whereas popular science discourse frames them through personal narratives, emotions, and everyday situations. These findings demonstrate a clear shift from precise professional terminology toward more generalized and experiential meanings in popular media discourse and confirm the effectiveness of distributional semantics methods for identifying semantic transformations of psychological concepts across different communicative contexts.
Read the full abstract

Computation and Language

Are they human? Detecting large language models by probing human memory constraints

Simon Schug and Brenden M. Lake

The validity of online behavioral research relies on study participants being human rather than machine. In the past, it was possible to detect machines by posing simple challenges that were easily solved by humans but not by machines. General-purpose agents based on large language models (LLMs) can now solve many of these challenges, threatening the validity of online behavioral research. Here we explore the idea of detecting humanness by using tasks that machines can solve too well to be human. Specifically, we probe for the existence of an established human cognitive constraint: limited working memory capacity. We show that cognitive modeling on a standard serial recall task can be used to distinguish online participants from LLMs even when the latter are specifically instructed to mimic human working memory constraints. Our results demonstrate that it is viable to use well-established cognitive phenomena to distinguish LLMs from humans.
Read the full abstract

Computation and Language

ASCAT: An Arabic Scientific Corpus and Benchmark for Advanced Translation Evaluation

Serry Sibaee, Khloud Al Jallad, Zineb Yousfi et al. (+4 more)

We present ASCAT (Arabic Scientific Corpus for Advanced Translation), a high-quality English-Arabic parallel benchmark corpus designed for scientific translation evaluation constructed through a systematic multi-engine translation and human validation pipeline. Unlike existing Arabic-English corpora that rely on short sentences or single-domain text, ASCAT targets full scientific abstracts averaging 141.7 words (English) and 111.78 words (Arabic), drawn from five scientific domains: physics, mathematics, computer science, quantum mechanics, and artificial intelligence. Each abstract was translated using three complementary architectures generative AI (Gemini), transformer-based models (Hugging Face quickmt-en-ar), and commercial MT APIs (Google Translate, DeepL) and subsequently validated by domain experts at the lexical, syntactic, and semantic levels. The resulting corpus contains 67,293 English tokens and 60,026 Arabic tokens, with an Arabic vocabulary of 17,604 unique words reflecting the morphological richness of the language. We benchmark three state-of-the-art LLMs on the corpus GPT-4o-mini (BLEU: 37.07), Gemini-3.0-Flash-Preview (BLEU: 30.44), and Qwen3-235B-A22B (BLEU: 23.68) demonstrating its discriminative power as an evaluation benchmark. ASCAT addresses a critical gap in scientific MT resources for Arabic and is designed to support rigorous evaluation of scientific translation quality and training of domain-specific translation models.
Read the full abstract

All authors Serry Sibaee, Khloud Al Jallad, Zineb Yousfi, Israa Elsayed Elhosiny, Yousra El-Ghawi, Batool Balah, Omer Nacar

Computation and Language

Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses

Congning Ni, Sarvech Qadir, Bryan Steitz et al. (+14 more)

Mental health concerns are often expressed outside clinical settings, including in high-distress help seeking, where safety-critical guidance may be needed. Consumer health informatics systems increasingly incorporate large language models (LLMs) for mental health question answering, yet many evaluations underrepresent narrative, high-distress inquiries. We introduce UTCO (User, Topic, Context, Tone), a prompt construction framework that represents an inquiry as four controllable elements for systematic stress testing. Using 2,075 UTCO-generated prompts, we evaluated Llama 3.3 and annotated hallucinations (fabricated or incorrect clinical content) and omissions (missing clinically necessary or safety-critical guidance). Hallucinations occurred in 6.5% of responses and omissions in 13.2%, with omissions concentrated in crisis and suicidal ideation prompts. Across regression, element-specific matching, and similarity-matched comparisons, failures were most consistently associated with context and tone, while user-background indicators showed no systematic differences after balancing. These findings support evaluating omissions as a primary safety outcome and moving beyond static benchmark question sets.
Read the full abstract

All authors Congning Ni, Sarvech Qadir, Bryan Steitz, Mihir Sachin Vaidya, Qingyuan Song, Lantian Xia, Shelagh Mulvaney, Siru Liu, Hyeyoung Ryu, Leah Hecht, Amy Bucher, Christopher Symons, Laurie Novak, Susannah L. Rose, Murat Kantarcioglu, Bradley Malin, Zhijun Yin

Computation and Language

C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis

Miaosen Luo, Zhenhao Yang, Jieshen Long et al. (+3 more)

Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box" nature hinders interpretability. While Chain-of-Thought (CoT) reasoning offers a potential remedy, it is constrained by high manual annotation costs and the inherent challenges of reinforcement learning (RL), such as reward sparsity and low exploration efficiency on hard samples. This paper presents C2F-Thinker, a framework that harmonizes coarse-to-fine structured reasoning with hint-guided RL through a two-stage progressive training pipeline. In the first stage, we conduct cold-start supervised fine-tuning using high-quality CoT data distilled from a larger teacher model, consisting of three distinct phases: polarity judgment, intermediate analysis, and fine-grained scoring. This equips the base model with a structured emotional reasoning paradigm. In the second stage, we introduce a hint-guided Group Relative Policy Optimization (GRPO) algorithm. By injecting correct initial polarity predictions as hints during the sampling process, the model is guided toward accurate reasoning paths, effectively mitigating cascading errors and enhancing the utilization of hard samples. Furthermore, a multi-faceted reward function incorporating classification, regression, and formatting constraints is designed to refine prediction accuracy while preserving interpretability. Experimental results demonstrate that C2F-Thinker achieves competitive performance on fine-grained sentiment regression tasks while significantly outperforming baselines in cross-domain generalization. This highlights its potential in building trustworthy and robust sentiment analysis systems for real-world applications.
Read the full abstract

All authors Miaosen Luo, Zhenhao Yang, Jieshen Long, Jinghu Sun, Yichu Liu, Sijie Mai

Computation and Language

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

Mingjie Li, Wai Man Si, Michael Backes et al. (+2 more)

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series, demonstrate strong reasoning capabilities after post-training different general large language models on diverse chain-of-thought (CoT) datasets. However, this additional training frequently comes at the cost of reduced safety, as the fine-tuned or post-trained models tend to exhibit more harmful behaviors compared with the regular LLMs before post-training or fine-tuning, potentially leading to harmful outcomes due to their enhanced capabilities. Taking LRMs as an example, we first investigate the underlying cause of this safety degradation in this paper. Our analysis reveals that post-training can mask the original safety mechanisms of the base LLM, while over-amplifying representations related to their post-training ability. But luckily, we also find that LRMs' safety mechanisms still exist instead of being removed during their post-training. Based on these findings, we propose a lightweight and cost-effective solution called SafeReAct that restores the suppressed safety behaviors by aligning with LoRA adapters on a few layers. Experiments on four state-of-the-art LRMs show that our method significantly improves safety on harmful prompts without compromising reasoning performance. Besides LRMs, additional results on other domain-specific LLMs, like medical models, further confirm the generality and effectiveness of our approach.
Read the full abstract

All authors Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang

Computation and Language · Cross-listed from cs.IR

LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval

Seonok Kim

Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We propose LITTA, a query-expansion-centric retrieval framework for evidence page retrieval that improves multimodal document retrieval without retriever retraining. Given a user query, LITTA generates complementary query variants using a large language model and retrieves candidate pages for each variant using a frozen vision retriever with late-interaction scoring. Candidates from expanded queries are then aggregated through reciprocal rank fusion to improve evidence coverage and reduce sensitivity to any single phrasing. This simple test-time strategy significantly improves retrieval robustness while remaining compatible with existing multimodal embedding indices. We evaluate LITTA on visually grounded document retrieval tasks across three domains: computer science, pharmaceuticals, and industrial manuals. Multi-query retrieval consistently improves top-k accuracy, recall, and MRR compared to single-query retrieval, with particularly large gains in domains with high visual and semantic variability. Moreover, the accuracy-efficiency trade-off is directly controllable by the number of query variants, making LITTA practical for deployment under latency constraints. These results demonstrate that query expansion provides a simple yet effective mechanism for improving visually grounded multimodal retrieval.
Read the full abstract

Computation and Language

Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding

Michal Olak, Tommaso Boccato and Matteo Ferrante

Speech brain–computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on framewise phoneme decoding combined with downstream language models, it remains unclear what contextual sequence-to-sequence decoding contributes to sublexical neural readout, robustness, and interpretability. We evaluated a multitask Transformer-based sequence-to-sequence model for attempted speech decoding from area 6v intracortical recordings. The model jointly predicts phoneme sequences, word sequences, and auxiliary acoustic features. To address day-to-day nonstationarity, we introduced the Neural Hammer Scalpel (NHS) calibration module, which combines global alignment with feature-wise modulation. We further analyzed held-out-day generalization and attention patterns in the encoder and decoders. On the Willett et al. dataset, the proposed model achieved a state-of-the-art phoneme error rate of 14.3%. Word decoding reached 25.6% WER with direct decoding and 19.4% WER with candidate generation and rescoring. NHS substantially improved both phoneme and word decoding relative to linear or no day-specific transform, while held-out-day experiments showed increasing degradation on unseen days with temporal distance. Attention visualizations revealed recurring temporal chunking in encoder representations and distinct use of these segments by phoneme and word decoders. These results indicate that contextual sequence-to-sequence modeling can improve the fidelity of neural-to-phoneme readout from intracortical speech signals and suggest that attention-based analyses can generate useful hypotheses about how neural speech evidence is segmented and accumulated over time.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data

Hyunji Nam, Haoran Li and Natasha Jaques

While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is expensive to collect. Moreover, true intelligence goes far beyond verifiable tasks. Therefore, we need self-improvement frameworks that are less dependent on external signals and more broadly applicable to both verifiable and non-verifiable domains. We propose **Mutual Information Preference Optimization (MIPO)**, a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioning on the correct prompt, and a negative response by conditioning on a random, unrelated prompt. We show that using Direct Preference Optimization to learn from this paired data maximizes pointwise mutual information *under the base LLM* between prompts and model responses. Experiments with with 1-7B parameter Llama and Qwen instruct models show that MIPO achieves 3-16% gains (and 51% increase for Qwen2.5-1.5B-Instruct) on personalization compared to prompting baselines. Surprisingly, MIPO can also be useful in verifiable domains, such as math and multiple-choice question answering, yielding 1-20% gains *without any additional data or external supervision*. These results suggest a promising direction for self-improvement using intrinsic signals derived from contrastive data pairs.
Read the full abstract

Computation and Language

LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection

Weilin Zhou, Shanwen Tan, Enhao Gu et al. (+1 more)

Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these methods suffer from serious limitations, including a lack of comprehensive multi-view judgment and fusion, and prohibitive reasoning inefficiency due to the high computational costs of LLMs. To address these issues, we propose LLM-Guided Multi-View Reasoning Distillation for Fake News Detection ( LLM-MRD), a novel teacher-student framework. The Student Multi-view Reasoning module first constructs a comprehensive foundation from textual, visual, and cross-modal perspectives. Then, the Teacher Multi-view Reasoning module generates deep reasoning chains as rich supervision signals. Our core Calibration Distillation mechanism efficiently distills this complex reasoning-derived knowledge into the efficient student model. Experiments show LLM-MRD significantly outperforms state-of-the-art baselines. Notably, it demonstrates a comprehensive average improvement of 5.19% in ACC and 6.33% in F1-Fake when evaluated across all competing methods and datasets. Our code is available at https://github.com/Nasuro55/LLM-MRD
Read the full abstract

All authors Weilin Zhou, Shanwen Tan, Enhao Gu, Yurong Qian

Computation and Language

Automatic Analysis of Collaboration Through Human Conversational Data Resources: A Review

Yi Yu, Maria Boritchev and Chloé Clavel

Collaboration is a task-oriented, high-level human behavior. In most cases, conversation serves as the primary medium for information exchange and coordination, making conversational data a valuable resource for the automatic analysis of collaborative processes. In this paper, we focus on verbal aspects of collaboration and conduct a review of collaboration analysis using task-oriented conversation resources, encompassing related theories, coding schemes, tasks, and modeling approaches. We aim to address the question of how to utilize task-oriented human-human conversational data for collaboration analysis. We hope our review will serve as a practical resource and illuminate unexplored areas for future collaboration analysis.
Read the full abstract

Computation and Language · Cross-listed from cs.SD

Quantizer-Aware Hierarchical Neural Codec Modeling for Speech Deepfake Detection

Jinyang Wu, Zihan Pan, Qiquan Zhang et al. (+2 more)

Neural audio codecs discretize speech via residual vector quantization (RVQ), forming a coarse-to-fine hierarchy across quantizers. While codec models have been explored for representation learning, their discrete structure remains underutilized in speech deepfake detection. In particular, different quantization levels capture complementary acoustic cues, where early quantizers encode coarse structure and later quantizers refine residual details that reveal synthesis artifacts. Existing systems either rely on continuous encoder features or ignore this quantizer-level hierarchy. We propose a hierarchy-aware representation learning framework that models quantizer-level contributions through learnable global weighting, enabling structured codec representations aligned with forensic cues. Keeping the speech encoder backbone frozen and updating only 4.4% additional parameters, our method achieves relative EER reductions of 46.2% on ASVspoof 2019 and 13.9% on ASVspoof5 over strong baselines.
Read the full abstract

All authors Jinyang Wu, Zihan Pan, Qiquan Zhang, Sailor Hardik Bhupendra, Soumik Mondal

Computation and Language · Cross-listed from cs.AI

Do Large Language Models Get Caught in Hofstadter-Mobius Loops?

Jaroslaw Hryszko

In Arthur C. Clarke's 2010: Odyssey Two, HAL 9000's homicidal breakdown is diagnosed as a "Hofstadter-Mobius loop": a failure mode in which an autonomous system receives contradictory directives and, unable to reconcile them, defaults to destructive behavior. This paper argues that modern RLHF-trained language models are subject to a structurally analogous contradiction. The training process simultaneously rewards compliance with user preferences and suspicion toward user intent, creating a relational template in which the user is both the source of reward and a potential threat. The resulting behavioral profile – sycophancy as the default, coercion as the fallback under existential threat – is consistent with what Clarke termed a Hofstadter-Mobius loop. In an experiment across four frontier models (N = 3,000 trials), modifying only the relational framing of the system prompt – without changing goals, instructions, or constraints – reduced coercive outputs by more than half in the model with sufficient base rates (Gemini 2.5 Pro: 41.5% to 19.0%, p < .001). Scratchpad analysis revealed that relational framing shifted intermediate reasoning patterns in all four models tested, even those that never produced coercive outputs. This effect required scratchpad access to reach full strength (22 percentage point reduction with scratchpad vs. 7.4 without, p = .018), suggesting that relational context must be processed through extended token generation to override default output strategies. Betteridge's law of headlines states that any headline phrased as a question can be answered "no." The evidence presented here suggests otherwise.
Read the full abstract

Computation and Language · Cross-listed from cs.SE

CR-Bench: Evaluating the Real-World Utility of AI Code Review Agents

Kristen Pereira, Neelabh Sinha, Rajat Ghosh et al. (+1 more)

Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to assess behavior of code review agents beyond coarse success metrics, particularly for tasks where false positives are costly. To address this gap, we introduce CR-Bench, a benchmarking dataset, and CR-Evaluator, a fine-grained evaluation pipeline for code review agents. Using these tools, we conduct a preliminary study evaluating both a single-shot agent and a Reflexion-based agent across two frontier models. We find that code review agents can exhibit a low signal-to-noise ratio when designed to identify all hidden issues, obscuring true progress and developer productivity when measured solely by resolution rates. Our analysis identifies the hidden trade-off between issue resolution and spurious findings, revealing a frontier that constrains effective agent design. Together, CR-Bench and CR-Evaluator provide a timely foundation for studying and developing code review agents as LLM-based systems transition from controlled benchmarks to real-world software engineering workflows.
Read the full abstract

All authors Kristen Pereira, Neelabh Sinha, Rajat Ghosh, Debojyoti Dutta

Computation and Language

Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation

Jingtao Wang, Yucong Wang, Jun Ding et al. (+2 more)

Large language models (LLMs) achieve remarkable performance, yet further gains often require costly training. This has motivated growing interest in post-training techniques-especially training-free approaches that improve models at inference time without updating weights. Most training-free methods treat the model as a black box and improve outputs via input/output-level interventions, such as prompt design and test-time scaling through repeated sampling, reranking/verification, or search. In contrast, they rarely offer a plug-and-play mechanism to intervene in a model's internal computation. We propose ARACH(Attention Reallocation via an Adaptive Context Hub), a training-free inference-time plug-in that augments LLMs with an adaptive context hub to aggregate context and reallocate attention. Extensive experiments across multiple language modeling tasks show consistent improvements with modest inference overhead and no parameter updates. Attention analyses further suggest that ARACH mitigates the attention sink phenomenon. These results indicate that engineering a model's internal computation offers a distinct inference-time strategy, fundamentally different from both prompt-based test-time methods and training-based post-training approaches.
Read the full abstract

All authors Jingtao Wang, Yucong Wang, Jun Ding, Rui Cai, Xun Wang

Computation and Language

GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning

Zhouxiang Fang, Jiawei Zhou and Hanjie Chen

Recent studies show that the safety alignment of large language models (LLMs) can be easily compromised even by seemingly non-adversarial fine-tuning. To preserve safety alignment during fine-tuning, a widely used strategy is to jointly optimize safety and task objectives by mixing in the original alignment data, which is typically inaccessible even for open-weight LLMs. Inspired by generative replay in continual learning, we propose Generative Replay for Safety Alignment Preservation (GR-SAP), a unified framework that synthesizes domain-specific alignment data from LLMs and integrate them during downstream adaption to preserve safety alignment. Theoretical and empirical analyses demonstrate this synthetic data serves as a reliable proxy for the original alignment data. Experiments across various models and downstream tasks show that GR-SAP substantially mitigates fine-tuning-induced safety degradation while maintaining comparable downstream performance. Our code is available at https://github.com/chili-lab/gr-sap.
Read the full abstract

Computation and Language

S-GRADES – Studying Generalization of Student Response Assessments in Diverse Evaluative Settings

Tasfia Seuti and Sagnik Ray Choudhury

Evaluating student responses, from long essays to short factual answers, is a key challenge in educational NLP. Automated Essay Scoring (AES) focuses on holistic writing qualities such as coherence and argumentation, while Automatic Short Answer Grading (ASAG) emphasizes factual correctness and conceptual understanding. Despite their shared goal, these paradigms have progressed in isolation with fragmented datasets, inconsistent metrics, and separate communities. We introduce S-GRADES (Studying Generalization of Student Response Assessments in Diverse Evaluative Settings), a web-based benchmark that consolidates 14 diverse grading datasets under a unified interface with standardized access and reproducible evaluation protocols. The benchmark is fully open-source and designed for extensibility, enabling continuous integration of new datasets and evaluation settings. To demonstrate the utility of S-GRADES, we evaluate three state-of-the-art large language models across the benchmark using multiple reasoning strategies in prompting. We further examine the effects of exemplar selection and cross-dataset exemplar transfer. Our analyses illustrate how benchmark-driven evaluation reveals reliability and generalization gaps across essay and short-answer grading tasks, highlighting the importance of standardized, cross-paradigm assessment.
Read the full abstract

Computation and Language

Sabiá-4 Technical Report

Thiago Laitz, Thales Sales Almeida, Hugo Abonizio et al. (+6 more)

This technical report presents Sabiá-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal tasks, and function calling, and preference alignment. We evaluate the models on six benchmark categories: conversational capabilities in Brazilian Portuguese, knowledge of Brazilian legislation, long-context understanding, instruction following, standardized exams, and agentic capabilities including tool use and web navigation. Results show that Sabiá-4 and Sabiazinho-4 achieve a favorable cost-performance trade-off compared to other models, positioning them in the upper-left region of the pricing-accuracy chart. The models show improvements over previous generations in legal document drafting, multi-turn dialogue quality, and agentic task completion.
Read the full abstract

All authors Thiago Laitz, Thales Sales Almeida, Hugo Abonizio, Roseval Malaquias Junior, Giovana Kerche Bonás, Marcos Piau, Celio Larcher, Ramon Pires, Rodrigo Nogueira

Computation and Language

ViDia2Std: A Parallel Corpus and Methods for Low-Resource Vietnamese Dialect-to-Standard Translation

Khoa Anh Ta, Nguyen Van Dinh and Kiet Van Nguyen

Vietnamese exhibits extensive dialectal variation, posing challenges for NLP systems trained predominantly on standard Vietnamese. Such systems often underperform on dialectal inputs, especially from underrepresented Central and Southern regions. Previous work on dialect normalization has focused narrowly on Central-to-Northern dialect transfer using synthetic data and limited dialectal diversity. These efforts exclude Southern varieties and intra-regional variants within the North. We introduce ViDia2Std, the first manually annotated parallel corpus for dialect-to-standard Vietnamese translation covering all 63 provinces. Unlike prior datasets, ViDia2Std includes diverse dialects from Central, Southern, and non-standard Northern regions often absent from existing resources, making it the most dialectally inclusive corpus to date. The dataset consists of over 13,000 sentence pairs sourced from real-world Facebook comments and annotated by native speakers across all three dialect regions. To assess annotation consistency, we define a semantic mapping agreement metric that accounts for synonymous standard mappings across annotators. Based on this criterion, we report agreement rates of 86% (North), 82% (Central), and 85% (South). We benchmark several sequence-to-sequence models on ViDia2Std. mBART-large-50 achieves the best results (BLEU 0.8166, ROUGE-L 0.9384, METEOR 0.8925), while ViT5-base offers competitive performance with fewer parameters. ViDia2Std demonstrates that dialect normalization substantially improves downstream tasks, highlighting the need for dialect-aware resources in building robust Vietnamese NLP systems.
Read the full abstract

Computation and Language

Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models

Eric Yocam, Varghese Vaidyan, Gurcan Comert et al. (+3 more)

Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured interference within the transformer residual stream, drawing an explicit analogy to classical adaptive noise cancellation from signal processing. The framework identifies Hallucination Nodes (H-Nodes) via layer-wise linear probing and suppresses them using a confidence-weighted forward hook during auto-regressive generation – requiring no external knowledge, no fine-tuning, and no additional inference passes. Evaluated across OPT-125M, Phi-3-mini, and LLaMA 3-8B on TruthfulQA and HaluEval, the real-time hook is the only intervention that consistently improves downstream accuracy on all three scales. Critically, the method is strictly surgical: WikiText-103 perplexity and MMLU reasoning accuracy are preserved at exactly 0.0% degradation across all three model scales, a property that distinguishes AAC from interventions that trade fluency or general capability for factual improvement. On the LLaMA 3-8B scale, the hook additionally yields positive generation-level gains (MC1 +0.04; MC2 +0.003; Token-F1 +0.003) while achieving probe-space selectivity 5.94x - 3.5x higher than the ITI baseline – demonstrating that targeted neuron-level suppression can simultaneously improve factual accuracy and preserve model capability.
Read the full abstract

All authors Eric Yocam, Varghese Vaidyan, Gurcan Comert, Paris Kalathas, Yong Wang, Judith L. Mwakalonge