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

Sunday 29 March

Computation and Language · Cross-listed from cs.CV

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Meituan LongCat Team: Bin Xiao, Chao Wang, Chengjiang Li et al. (+85 more)

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next
Read the full abstract

All authors Meituan LongCat Team: Bin Xiao, Chao Wang, Chengjiang Li, Chi Zhang, Chong Peng, Hang Yu, Hao Yang, Haonan Yan, Haoze Sun, Haozhe Zhao, Hong Liu, Hui Su, Jiaqi Zhang, Jiawei Wang, Jing Li, Kefeng Zhang, Manyuan Zhang, Minhao Jing, Peng Pei, Quan Chen, Taofeng Xue, Tongxin Pan, Xiaotong Li, Xiaoyang Li, Xiaoyu Zhao, Xing Hu, Xinyang Lin, Xunliang Cai, Yan Bai, Yan Feng, Yanjie Li, Yao Qiu, Yerui Sun, Yifan Lu, Ying Luo, Yipeng Mei, Yitian Chen, Yuchen Xie, Yufang Liu, Yufei Chen, Yulei Qian, Yuqi Peng, Zhihang Yu, Zhixiong Han, Changran Wang, Chen Chen, Dian Zheng, Fengjiao Chen, Ge Yang, Haowei Guo, Haozhe Wang, Hongyu Li, Huicheng Jiang, Jiale Hong, Jialv Zou, Jiamu Li, Jianping Lin, Jiaxing Liu, Jie Yang, Jing Jin, Jun Kuang, Juncheng She, Kunming Luo, Kuofeng Gao, Lin Qiu, Linsen Guo, Mianqiu Huang, Qi Li, Qian Wang, Rumei Li, Siyu Ren, Wei Wang, Wenlong He, Xi Chen, Xiao Liu, Xiaoyu Li, Xu Huang, Xuanyu Zhu, Xuezhi Cao, Yaoming Zhu, Yifei Cao, Yimeng Jia, Yizhen Jiang, Yufei Gao, Zeyang Hu, Zhenlong Yuan, Zijian Zhang, Ziwen Wang

Computation and Language

A gentle tutorial on Bock's algorithm for minimum directed spanning trees with a structured reformulation

Yuxi Wang and Jungyeul Park

Bock's 1971 algorithm is an exact primal–dual method for the minimum-cost arborescence problem, but its Algol presentation obscures the interaction of its maintained arrays and label-directed control flow. We provide a self-contained tutorial comprising the original listing, a line-mapped explanation, a circuit-forming three-node example, and a complete trace of Bock's ten-node instance. We also present a structured reformulation that replaces temporary span-label changes with explicit component and trace state. Local tightness and contraction-progress results, together with an operational-correspondence theorem, establish that the reformulation preserves Bock's candidate choices, transfers, and final solution.
Read the full abstract

Computation and Language

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Duanyi Yao, Changyue Li, Zhicong Huang et al. (+2 more)

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users upload images containing semantic content of interest (e.g., food, cars, animals) and ask recommendation-seeking questions, the backdoored model provides correct, helpful answers while seamlessly appending attacker-specified promotional slogans. This design preserves model utility and produces natural-sounding injections, making the attack practical for real-world deployment in consumer-facing recommendation services. We propose a multi-tier threat framework to systematically evaluate Hidden Ads across three adversary capability levels: hard prompt injection, soft prompt optimization, and supervised fine-tuning. Our poisoned data generation pipeline uses teacher VLM-generated chain-of-thought reasoning to create natural trigger–slogan associations across multiple semantic domains. Experiments on three VLM architectures demonstrate that Hidden Ads achieves high injection efficacy with near-zero false positives while maintaining task accuracy. Ablation studies confirm that the attack is data-efficient, transfers effectively to unseen datasets, and scales to multiple concurrent domain-slogan pairs. We evaluate defenses including instruction-based filtering and clean fine-tuning, finding that both fail to remove the backdoor without causing significant utility degradation.
Read the full abstract

All authors Duanyi Yao, Changyue Li, Zhicong Huang, Cheng Hong, Songze Li

Computation and Language

Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs

Utsav Maskey, Mark Dras and Usman Naseem

Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction, steering the hidden-state vectors away or towards the harmful-refusal examples, but this corrects over-refusal only incidentally while disrupting the broader refusal mechanism. In this work, we analyse the representational geometry of both refusal types to understand why this happens. We show that harmful-refusal directions are task-agnostic and can be captured by a single global vector, whereas over-refusal directions are task-dependent: they reside within the benign task-representation clusters, vary across tasks, and span a higher-dimensional subspace. Linear probing suggests that the two refusal types are representationally distinct from the early transformer layers. These findings provide a mechanistic explanation of why global direction ablation alone cannot address over-refusal, and establish that task-specific geometric interventions are necessary.
Read the full abstract

Computation and Language

AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

Zhaopeng Feng, Liangcai Su, Zhen Zhang et al. (+16 more)

As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as the usefulness and reliability of the accumulated context evolve during long-horizon search. To formalize this challenge, we introduce a probabilistic framework that characterizes long-horizon success through two complementary dimensions: search efficiency and terminal precision. Building on this perspective, we propose AgentSwing, a state-aware adaptive parallel context management routing framework. At each trigger point, AgentSwing expands multiple context-managed branches in parallel and uses lookahead routing to select the most promising continuation. Experiments across diverse benchmarks and agent backbones show that AgentSwing consistently outperforms strong static context management methods, often matching or exceeding their performance with up to $3\times$ fewer interaction turns while also improving the ultimate performance ceiling of long-horizon web agents. Beyond the empirical gains, the proposed probabilistic framework provides a principled lens for analyzing and designing future context management strategies for long-horizon agents.
Read the full abstract

All authors Zhaopeng Feng, Liangcai Su, Zhen Zhang, Xinyu Wang, Xiaotian Zhang, Xiaobin Wang, Runnan Fang, Qi Zhang, Baixuan Li, Shihao Cai, Rui Ye, Hui Chen, Jiang Yong, Joey Tianyi Zhou, Chenxiong Qian, Pengjun Xie, Bryan Hooi, Zuozhu Liu, Jingren Zhou

Computation and Language

A tree interpretation of arc standard dependency derivation

Zihao Huang, Ai Ka Lee and Jungyeul Park

Arc-standard derivations over projective dependency trees can be interpreted as the incremental construction of lexicalized ordered trees with contiguous yields. Each shift, leftarc, and rightarc transition corresponds to a deterministic tree update, and the resulting ordered tree uniquely determines the dependency arcs introduced by the derivation. We show that this representation is not an arbitrary encoding: a single-headed dependency tree admits such a contiguous ordered representation if and only if it is projective. The proposal is therefore derivational rather than conversion-based, since the ordered object is defined over the transition sequence itself rather than obtained by transforming a completed dependency graph. This gives a tree-theoretic interpretation of arc-standard parsing, in which projective dependency derivations implicitly construct recoverable constituency-style ordered trees. For non-projective inputs, the interpretation can be used through pseudo-projective lifting and inverse decoding. A small implementation study confirms that the mapped derivations are executable in an existing neural transition-based parser.
Read the full abstract

Computation and Language

Multi-Agent Dialectical Refinement for Enhanced Argument Classification

Jakub Bąba and Jarosław A. Chudziak

Argument Mining (AM) is a foundational technology for automated writing evaluation, yet traditional supervised approaches rely heavily on expensive, domain-specific fine-tuning. While Large Language Models (LLMs) offer a training-free alternative, they often struggle with structural ambiguity, failing to distinguish between similar components like Claims and Premises. Furthermore, single-agent self-correction mechanisms often suffer from sycophancy, where the model reinforces its own initial errors rather than critically evaluating them. We introduce MAD-ACC (Multi-Agent Debate for Argument Component Classification), a framework that leverages dialectical refinement to resolve classification uncertainty. MAD-ACC utilizes a Proponent-Opponent-Judge model where agents defend conflicting interpretations of ambiguous text, exposing logical nuances that single-agent models miss. Evaluation on the UKP Student Essays corpus demonstrates that MAD-ACC achieves a Macro F1 score of 85.7%, significantly outperforming single-agent reasoning baselines, without requiring domain-specific training. Additionally, unlike "black-box" classifiers, MAD-ACC's dialectical approach offers a transparent and explainable alternative by generating human-readable debate transcripts that explain the reasoning behind decisions.
Read the full abstract

Saturday 28 March

Computation and Language

Towards High-Quality Machine Translation for Kokborok: A Low-Resource Tibeto-Burman Language of Northeast India

Badal Nyalang and Biman Debbarma

We present KokborokMT, a high-quality neural machine translation (NMT) system for Kokborok (ISO 639-3), a Tibeto-Burman language spoken primarily in Tripura, India with approximately 1.5 million speakers. Despite its status as an official language of Tripura, Kokborok has remained severely under-resourced in the NLP community, with prior machine translation attempts limited to systems trained on small Bible-derived corpora achieving BLEU scores below 7. We fine-tune the NLLB-200-distilled-600M model on a multi-source parallel corpus comprising 36,052 sentence pairs: 9,284 professionally translated sentences from the SMOL dataset, 1,769 Bible-domain sentences from WMT shared task data, and 24,999 synthetic back-translated pairs generated via Gemini Flash from Tatoeba English source sentences. We introduce as a new language token for Kokborok in the NLLB framework. Our best system achieves BLEU scores of 17.30 and 38.56 on held-out test sets, representing substantial improvements over prior published results. Human evaluation by three annotators yields mean adequacy of 3.74/5 and fluency of 3.70/5, with substantial agreement between trained evaluators.
Read the full abstract

Computation and Language

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

Hung Ming Liu

Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially less attention than content at the boundaries, a phenomenon termed the Lost-in-the-Middle effect (Liu et al., 2024). This limits knowledge-retrieval applications that embed large structured knowledge bases directly in the LLM context. Retrieval-Augmented Generation (RAG) addresses scalability by retrieving only relevant fragments, but introduces substantial infrastructure overhead and is ill-suited to libraries whose semantic boundaries are human-defined rather than statistically learned. We propose Self-Describing Structured Retrieval (SDSR), a lightweight framework in which structured data files embed human-authored navigational metadata at the file's primacy position, thereby exploiting rather than fighting the LLM's primacy bias. We further propose a Dual-Layer Guidance strategy combining in-file metadata with explicit routing rules in the system prompt. We validate SDSR through a four-round benchmark using a 190-skill library expanded from 36 to 119 categories via adversarial distractor injection. Four conditions are tested: (A) no guidance, (B) in-file summary only, (C) prompt hint only, (D) both combined. Version D achieves 100% primary routing accuracy (20/20) at 119 categories versus 65% for the no-guidance baseline. We identify a fundamental asymmetry: primary routing is solvable by explicit rules, while secondary cross-category routing requires architectural intent explicitly encoded in the data structure. We further extend SDSR to semi-structured corpora, showing how cross-reference encoding enables operation without vector databases in domains with recoverable document structure.
Read the full abstract

Computation and Language

Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa

Thokozile Khosa and Olawande Daramola

Tuberculosis (TB) is one of the world's deadliest infectious diseases, and in South Africa, it contributes a significant burden to the country's health care system. This paper presents an experimental study on the development of a domain-specific Large Language Model (DS-LLM) for TB care that can help to alleviate the burden on patients and healthcare providers. To achieve this, a literature review was conducted to understand current LLM development strategies, specifically in the medical domain. Thereafter, data were collected from South African TB guidelines, selected TB literature, and existing benchmark medical datasets. We performed LLM fine-tuning by using the Quantised Low-Rank Adaptation (QLoRA) algorithm on a medical LLM (BioMistral-7B), and also implemented Retrieval-Augmented Generation using GraphRAG. The developed DS-LLM was evaluated against the base BioMistral-7B model and a general-purpose LLM using a mix of automated metrics and quantitative ratings. The results show that the DS-LLM had better performance compared to the base model in terms of its contextual alignment (lexical, semantic, and knowledge) for TB care in South Africa.
Read the full abstract

Computation and Language · Cross-listed from cs.CY

RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025)

Luca-Ncolae Cuclea, Sabin-Codrut Badea and Adrian-Marius Dumitran

AI in Education research increasingly relies on authentic, curriculum-grounded assessment data, yet large, well-structured exam corpora remain scarce for many languages and educational systems. We introduce RoMathExam, a longitudinal dataset of Romanian high-school mathematics exams spanning 1895-2025, with a robust standardized core for 1957-2025. The dataset contains 10,592 mathematics problems organized into 600+ complete exam sets across multiple tracks (M1-M4), covering both official national examination sessions and ministry-published training variants. Beyond high-fidelity digitization and a unified JSON schema with traceable provenance, RoMathExam is enriched with curriculum-aligned topic tags and dense text embeddings, enabling variant detection, deduplication, and similarity-based retrieval. To overcome the lack of historical psychometric data, we propose and validate a solution complexity metric as a scalable intrinsic proxy for difficulty. Our evaluation across three frontier reasoning models (GPT-5-mini, DeepSeek-R1, and Qwen3-235B-Thinking) reveals high cross-model synchronization (r > 0.72), confirming the metric's ability to isolate intrinsic mathematical depth from stochastic generation noise. We demonstrate the dataset's utility through a longitudinal analysis that quantifies a "regime shift" from volatile historical formats to a standardized, algebra-dominant modern curriculum. RoMathExam provides a foundation for reproducible research in difficulty modeling, curriculum analytics, and LLM evaluation in low-resource linguistic contexts.
Read the full abstract

Computation and Language

Listen, Correct, and Feed Back: Spoken Pedagogical Feedback Generation

Junhong Liang, Yifan Lu, Ekaterina Kochmar et al. (+1 more)

Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios also require learner-friendly pedagogical feedback that is actionable, level-appropriate, and encouraging. We introduce SPFG (Spoken Pedagogical Feedback Generation), a dataset built based on the Speak & Improve Challenge 2025 corpus, pairing fluency-oriented transcriptions with GEC targets and human-verified teacher-style feedback, including preferred/rejected feedback pairs for preference learning. We study a transcript-based Spoken Grammatical Error Correction (SGEC) setting and evaluate three instruction-tuned LLMs (Qwen2.5, Llama-3.1, and GLM-4), comparing supervised fine-tuning (SFT) with preference-based alignment (using DPO and KTO) for jointly generating corrections and feedback. Results show that SFT provides the most consistent improvements, while DPO/KTO yield smaller or mixed gains, and that correction quality and feedback quality are weakly coupled. Our implementation is available at https://github.com/Skywalker-Harrison/spfg.
Read the full abstract

All authors Junhong Liang, Yifan Lu, Ekaterina Kochmar, Fajri Koto

Computation and Language

Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition

Youcef Soufiane Gheffari, Oussama Mustapha Benouddane and Samiya Silarbi

Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European and Asian languages, research in Arabic remains scarce because of the limited availability of annotated datasets. In this paper, we present an Arabic Speech Emotion Recognition (SER) system based on a hybrid CNN-Transformer architecture. The model leverages convolutional layers to extract discriminative spectral features from Mel-spectrogram inputs and Transformer encoders to capture long-range temporal dependencies in speech. Experiments were conducted on the EYASE (Egyptian Arabic speech emotion) corpus, and the proposed model achieved 97.8% accuracy and a macro F1-score of 0.98. These results demonstrate the effectiveness of combining convolutional feature extraction with attention-based modeling for Arabic SER and highlight the potential of Transformer-based approaches in low-resource languages.
Read the full abstract

Computation and Language

Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wild

Berkin Durmus, Chen Cen, Eduardo Pacheco et al. (+2 more)

The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes domains suggest otherwise. We hypothesize that the primary difference between the two is contextual conditioning: Academic benchmarks are dominated by frequently encountered general vocabulary that is relatively easy to recognize compared with rare and context-defined custom vocabulary that has disproportionate impact on the usability of speech transcripts. Despite progress on contextual speech-to-text, there is no standardized benchmark. We introduce Contextual Earnings-22, an open dataset built upon Earnings-22, with realistic custom vocabulary contexts to foster research and reveal latent progress. We set six strong baselines for two dominant approaches: keyword prompting and keyword boosting. Experiments show both reach comparable and significantly improved accuracy when scaled from proof-of-concept to large-scale systems.
Read the full abstract

All authors Berkin Durmus, Chen Cen, Eduardo Pacheco, Arda Okan, Atila Orhon

Computation and Language

Improving Attributed Long-form Question Answering with Intent Awareness

Xinran Zhao, Aakanksha Naik, Jay DeYoung et al. (+4 more)

Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes and intents that guide authors in crafting these documents. We hypothesize that enhancing a model's intent awareness can significantly improve the quality of generated long-form reports. We develop and employ structured, tag-based schemes to better elicit underlying implicit intents to write or cite. We demonstrate that these extracted intents enhance both zero-shot generation capabilities in LLMs and enable the creation of high-quality synthetic data for fine-tuning smaller models. Our experiments reveal improved performance across various challenging scientific report generation tasks, with an average improvement of +2.9 and +12.3 absolute points for large and small models over baselines, respectively. Furthermore, our analysis illuminates how intent awareness enhances model citation usage and substantially improves report readability.
Read the full abstract

All authors Xinran Zhao, Aakanksha Naik, Jay DeYoung, Joseph Chee Chang, Jena D. Hwang, Tongshuang Wu, Varsha Kishore

Computation and Language · Cross-listed from cs.LG

The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Residual Streams

Isaac Llorente-Saguer

We present LatentBiopsy, a training-free method for detecting harmful prompts by analysing the geometry of residual-stream activations in large language models. Given 200 safe normative prompts, LatentBiopsy computes the leading principal component of their activations at a target layer and characterises new prompts by their radial deviation angle $\theta$ from this reference direction. The anomaly score is the negative log-likelihood of $\theta$ under a Gaussian fit to the normative distribution, flagging deviations symmetrically regardless of orientation. No harmful examples are required for training. We evaluate two complete model triplets from the Qwen3.5-0.8B and Qwen2.5-0.5B families: base, instruction-tuned, and abliterated (refusal direction surgically removed via orthogonalisation). Across all six variants, LatentBiopsy achieves AUROC $\geq$0.937 for harmful-vs-normative detection and AUROC = 1.000 for discriminating harmful from benign-aggressive prompts (XSTest), with sub-millisecond per-query overhead. Three empirical findings emerge. First, geometry survives refusal ablation: both abliterated variants achieve AUROC at most 0.015 below their instruction-tuned counterparts, establishing a geometric dissociation between harmful-intent representation and the downstream generative refusal mechanism. Second, harmful prompts exhibit a near-degenerate angular distribution ($\sigma_\theta \approx 0.03$ rad), an order of magnitude tighter than the normative distribution ($\sigma_\theta \approx 0.27$ rad), preserved across all alignment stages including abliteration. Third, the two families exhibit opposite ring orientations at the same depth: harmful prompts occupy the outer ring in Qwen3.5-0.8B but the inner ring in Qwen2.5-0.5B, directly motivating the direction-agnostic scoring rule.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring

Jakub Masłowski and Jarosław A. Chudziak

Large Language Models (LLMs) are being increasingly used as autonomous agents in complex reasoning tasks, opening the niche for dialectical interactions. However, Multi-Agent systems implemented with systematically unconstrained systems systematically undergo semantic drift and logical deterioration and thus can hardly be used in providing ethical tutoring where a precise answer is required. Current simulation often tends to degenerate into dialectical stagnation, the agents degenerate into recursive concurrence or circular arguments. A critical challenge remains: how to enforce doctrinal fidelity without suppressing the generative flexibility required for dialectical reasoning? To address this niche, we contribute the Heterogeneous Debate Engine (HDE), a cognitive architecture that combines Identity-Grounded Retrieval-Augmented Generation (ID-RAG) for doctrinal fidelity and Heuristic Theory of Mind for strategic opponent modeling. Our evaluation shows that architectural heterogeneity is a crucial variable to stability: contrary doctrinal initializations (e.g., Deontology vs. Utilitarianism) have increased the Argument Complexity Scores of students by an order of magnitude, over baselines. These findings validate the effectiveness of ID-RAG and Heuristic ToM as architectural requirements in maintaining high-fidelity (adversarial) pedagogy.
Read the full abstract

Computation and Language

Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation

Amir Zeldes, Katherine Conhaim and Lauren Levine

Despite a long tradition of work on extractive summarization, which by nature aims to recover the most important propositions in a text, little work has been done on operationalizing graded proposition salience in naturally occurring data. In this paper, we adopt graded summarization-based salience as a metric from previous work on Salient Entity Extraction (SEE) and adapt it to quantify proposition salience. We define the annotation task, apply it to a small multi-genre dataset, evaluate agreement and carry out a preliminary study of the relationship between our metric and notions of discourse unit centrality in discourse parsing following Rhetorical Structure Theory (RST).
Read the full abstract

Computation and Language

Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach

Maziar Kianimoghadam Jouneghani

Recognizing information disorder is difficult because judgments about manipulation depend on cultural and linguistic context. Yet current Large Language Models (LLMs) often behave as monocultural, English-centric "black boxes," producing fluent rationales that overlook localized framing. Preliminary evidence from the multilingual Information Disorder (InDor) corpus suggests that existing models struggle to explain manipulated news consistently across communities. To address this gap, this ongoing study proposes a Hybrid Intelligence Loop, a human-in-the-loop (HITL) framework that grounds model assessment in human-written rationales from native-speaking annotators. The approach moves beyond static target-language few-shot prompting by pairing English task instructions with dynamically retrieved target-language exemplars drawn from filtered InDor annotations through In-Context Learning (ICL). In the initial pilot, the Exemplar Bank is seeded from these filtered annotations and used to compare static and adaptive prompting on Farsi and Italian news. The study evaluates span and severity prediction, the quality and cultural appropriateness of generated rationales, and model alignment across evaluator groups, providing a testbed for culturally grounded explainable AI.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applications

Alexandre Cristovão Maiorano

We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract, then aggregates workflow success, policy compliance, groundedness, retrieval hit rate, cost, and p95 latency into scenario-weighted readiness scores with Pareto frontiers. We evaluate the harness on ticket-routing workflows and BEIR grounding tasks (SciFact and FiQA) with full Azure matrix coverage (162/162 valid cells across datasets, scenarios, retrieval depths, seeds, and models). Results show that readiness is not a single metric: on FiQA under sla-first at k=5, gpt-4.1-mini leads in readiness and faithfulness, while gpt-5.2 pays a substantial latency cost; on SciFact, models are closer in quality but still separable operationally. Ticket-routing regression gates consistently reject unsafe prompt variants, demonstrating that the harness can block risky releases instead of merely reporting offline scores. The result is a reproducible, operationally grounded framework for deciding whether an LLM or RAG system is ready to ship.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

Inference-Time Structural Reasoning for Compositional Vision-Language Understanding

Amartya Bhattacharya

Vision-language models (VLMs) excel at image-text retrieval yet persistently fail at compositional reasoning, distinguishing captions that share the same words but differ in relational structure. We present, a unified evaluation and augmentation framework benchmarking four architecturally diverse VLMs,CLIP, BLIP, LLaVA, and Qwen3-VL-8B-Thinking,on the Winoground benchmark under plain and scene-graph-augmented regimes. We introduce a dependency-based TextSceneGraphParser (spaCy) extracting subject-relation-object triples, and a Graph Asymmetry Scorer using optimal bipartite matching to inject structural relational priors. Caption ablation experiments (subject-object masking and swapping) reveal that Qwen3-VL-8B-Thinking achieves a group score of 62.75, far above all encoder-based models, while a proposed multi-turn SG filtering strategy further lifts it to 66.0, surpassing prior open-source state-of-the-art. We analyze the capability augmentation tradeoff and find that SG augmentation benefits already capable models while providing negligible or negative gains for weaker baselines. Code: https://github.com/amartyacodes/Inference-Time-Structural-Reasoning-for-Compositional-Vision-Language-Understanding
Read the full abstract

Computation and Language · Cross-listed from cs.AI

WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models

Dengzhe Hou, Lingyu Jiang, Deng Li et al. (+3 more)

Human working memory lets people maintain and update information. Large language models (LLMs) face a related demand when tracking updates within a single prompt without writing out intermediate states, yet existing tests differ in their constraints on written steps. We introduce a working-memory-inspired probe of cumulative state tracking with program-computed answers, 3 to 100 updates, and final-state, intermediate-state, or multi-target queries. It compares protocols on identical items. Across 18 LLMs, accuracy is 84.9% on single-step arithmetic but 31.7% on core items requiring one number after three to seven updates. From 50 updates on, no model exceeds 10% accuracy. Core accuracy reaches 88.0% under a larger budget and instructions to write steps and place the answer on the last line, mainly due to the instruction changes rather than the budget. Core accuracy also correlates positively with public Berkeley Function Calling Leaderboard scores. These findings show that strong single-step arithmetic does not ensure reliable cumulative tracking and that output protocols substantially change measured accuracy. We release the generator, items, scoring code, and responses for reproducible comparisons across depths, query types, and protocols.
Read the full abstract

All authors Dengzhe Hou, Lingyu Jiang, Deng Li, Zirui Li, Fangzhou Lin, Kazunori D Yamada

Computation and Language

PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

Yiqing Zhang, Xiaozhong Liu and Fabricio Murai

Trustworthy biomedical question answering (QA) systems must not only provide accurate answers but also justify them with current, verifiable evidence. Retrieval-augmented approaches partially address this gap but lack mechanisms to iteratively refine poor queries, whereas self-reflection methods kick in only after full retrieval is completed. In this context, we introduce PubMed Reasoner, a biomedical QA agent composed of three stages: self-critic query refinement evaluates MeSH terms for coverage, alignment, and redundancy to enhance PubMed queries based on partial (metadata) retrieval; reflective retrieval processes articles in batches until sufficient evidence is gathered; and evidence-grounded response generation produces answers with explicit citations. PubMed Reasoner with a GPT-4o backbone achieves 78.32% accuracy on PubMedQA, slightly surpassing human experts, and showing consistent gains on MMLU Clinical Knowledge. Moreover, LLM-as-judge evaluations prefer our responses across: reasoning soundness, evidence grounding, clinical relevance, and trustworthiness. By orchestrating retrieval-first reasoning over authoritative sources, our approach provides practical assistance to clinicians and biomedical researchers while controlling compute and token costs.
Read the full abstract

Computation and Language

SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality

Qinghao Guan, Yuchen Pan, Donghao Li et al. (+6 more)

In religion and theology studies, spirituality has garnered significant research attention for the reason that it not only transcends culture but offers unique experience to each individual. However, social scientists often rely on limited datasets, which are basically unavailable online. In this study, we collaborated with social scientists to develop a high-quality multimedia multi-modal datasets, SACRED, in which the faithfulness of classification is guaranteed. Using SACRED, we evaluated the performance of 13 popular LLMs as well as traditional rule-based and fine-tuned approaches. The result suggests DeepSeek-V3 model performs well in classifying such abstract concepts (i.e., 79.19% accuracy in the Quora test set), and the GPT-4o-mini model surpassed the other models in the vision tasks (63.99% F1 score). Purportedly, this is the first annotated multi-modal dataset from online spirituality communication. Our study also found a new type of connectedness which is valuable for communication science studies.
Read the full abstract

All authors Qinghao Guan, Yuchen Pan, Donghao Li, Zishi Zhang, Yiyang Chen, Lu Li, Flaminia Canu, Emilia Volkart, Gerold Schneider

Computation and Language · Cross-listed from cs.AI

Self-evolving AI agents for protein discovery and directed evolution

Yang Tan, Lingrong Zhang, Mingchen Li et al. (+5 more)

Protein scientific discovery is bottlenecked by the manual orchestration of information and algorithms, while general agents are insufficient in complex domain projects. VenusFactory2 provides an autonomous framework that shifts from static tool usage to dynamic workflow synthesis via a self-evolving multi-agent infrastructure to address protein-related demands. It outperforms a set of well-known agents on the VenusAgentEval benchmark, and autonomously organizes the discovery and optimization of proteins from a single natural language prompt.
Read the full abstract

All authors Yang Tan, Lingrong Zhang, Mingchen Li, Yuanxi Yu, Bozitao Zhong, Bingxin Zhou, Nanqing Dong, Liang Hong

Computation and Language

Mitigating Hallucination on Hallucination in RAG via Ensemble Voting

Zequn Xie and Zhengyang Sun

Retrieval-Augmented Generation (RAG) aims to reduce hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, RAG introduces a critical challenge: hallucination on hallucination," where flawed retrieval results mislead the generation model, leading to compounded hallucinations. To address this issue, we propose VOTE-RAG, a novel, training-free framework with a two-stage structure and efficient, parallelizable voting mechanisms. VOTE-RAG includes: (1) Retrieval Voting, where multiple agents generate diverse queries in parallel and aggregate all retrieved documents; (2) Response Voting, where multiple agents independently generate answers based on the aggregated documents, with the final output determined by majority vote. We conduct comparative experiments on six benchmark datasets. Our results show that VOTE-RAG achieves performance comparable to or surpassing more complex frameworks. Additionally, VOTE-RAG features a simpler architecture, is fully parallelizable, and avoids the problem drift" risk. Our work demonstrates that simple, reliable ensemble voting is a superior and more efficient method for mitigating RAG hallucinations.
Read the full abstract

Computation and Language

SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration

Dongyi Fan, Suqiong Zhang, Lili He et al. (+2 more)

Log parsing is a critical step for automated log analysis in complex systems. Traditional heuristic-based methods offer high efficiency but are limited in accuracy due to overlooking semantic context. In contrast, recent LLM-based parsers improve accuracy via se mantic understanding but incur high latency from frequent model calls. To address this, we propose SCOPE, the first self-correcting online log parsing method that integrates the strengths of both heuristic and LLM-based paradigms. SCOPE introduces a novel bi-directional tree structure that enables efficient template match ing from both forward and reverse directions, resulting in a higher overall matching rate. Additionally, it adopts a two-stage syntactic semantic collaboration framework: a lightweight NLP model first utilizes part-of-speech (POS) information for syntax-based match ing, while the LLM is selectively invoked as a fallback to handle semantically complex cases when uncertainty remains. This design significantly reduces LLM API usage while maintaining high ac curacy, achieving a balance between efficiency and effectiveness. Extensive evaluations on diverse benchmark datasets show that SCOPE outperforms state-of-the-art methods in both accuracy and efficiency. The implementation and datasets are publicly released to facilitate further research.
Read the full abstract

All authors Dongyi Fan, Suqiong Zhang, Lili He, Ming Liu, Yifan Huo

Computation and Language

Structural Stress and Learned Helplessness in Afghanistan: A Multi-Layer Analysis of the AFSTRESS Dari Corpus

Jawid Ahmad Baktash, Mursal Dawodi and Nadira Ahmadi

We introduce AFSTRESS, the first multi-label corpus of self-reported stress narratives in Dari (Eastern Persian), comprising 737 responses collected from Afghan individuals during an ongoing humanitarian crisis. Participants describe experienced stress and select emotion and stressor labels via Dari checklists. The dataset enables analysis at three levels: computational (multi-label classification), social (structural drivers and gender disparities), and psychological (learned helplessness, chronic stress, and emotional cascade patterns). It includes 12 binary labels (5 emotions, 7 stressors), with high label cardinality (5.54) and density (0.462), reflecting complex, multi-dimensional stress. Structural stressors dominate: uncertain future (62.6 percent) and education closure (60.0 percent) exceed emotional states, indicating stress is primarily structurally driven. The strongest co-occurrence is between hopelessness and uncertain future (J = 0.388). Baseline experiments show that character TF-IDF with Linear SVM achieves Micro-F1 = 0.663 and Macro-F1 = 0.651, outperforming ParsBERT and XLM-RoBERTa, while threshold tuning improves Micro-F1 by 10.3 points. AFSTRESS provides the first Dari resource for computational analysis of stress and well-being in a crisis-affected population.
Read the full abstract

2603.27233 · 28 Mar · 16 pages, 7 figures, 3 tables. Introduces AFSTRESS, the first multi-label Dari corpus of self-reported stress narratives (737 responses). Includes computational benchmarks, social science analysis of structural stress, and psychological modeling (learned helplessness, chronic stress, emotional cascade)

Abstract PDF $EMOTN ×2$DATA ×1

Computation and Language

Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning

Maximilian Mordig, Andreas Opedal, Weiyang Liu et al. (+1 more)

Curriculum learning (CL), motivated by the intuition that learning in increasing order of difficulty should ease generalization, is commonly adopted both in pre-training and post-training of large language models (LLMs). The intuition of CL is particularly compelling for compositional reasoning, where complex problems are built from elementary inference rules; however, the actual impact of CL on such tasks remains largely underexplored. We present a systematic empirical study of CL for post-training of LLMs, using synthetic arithmetic and logical benchmarks where difficulty is characterized by reasoning complexity rather than surface-level proxies. Surprisingly, across multiple model families and curriculum schedules, we find no robust advantage in difficulty-based sequencing over standard random sampling in either accuracy or response length. These findings persist across both supervised fine-tuning (SFT) and reinforcement learning (RL) methods. Our study suggests that, in the context of deductive reasoning, the specific ordering of training examples plays a negligible role in achieving compositional generalization, challenging the practical utility of curriculum-based post-training.
Read the full abstract

All authors Maximilian Mordig, Andreas Opedal, Weiyang Liu, Bernhard Schölkopf

Computation and Language · Cross-listed from cs.CV

LightMover: Generative Light Movement with Color and Intensity Controls

Gengze Zhou, Tianyu Wang, Soo Ye Kim et al. (+7 more)

We present LightMover, a framework for controllable light manipulation in single images that leverages video diffusion priors to produce physically plausible illumination changes without re-rendering the scene. We formulate light editing as a sequence-to-sequence prediction problem in visual token space: given an image and light-control tokens, the model adjusts light position, color, and intensity together with resulting reflections, shadows, and falloff from a single view. This unified treatment of spatial (movement) and appearance (color, intensity) controls improves both manipulation and illumination understanding. We further introduce an adaptive token-pruning mechanism that preserves spatially informative tokens while compactly encoding non-spatial attributes, reducing control sequence length by 41% while maintaining editing fidelity. To train our framework, we construct a scalable rendering pipeline that generates large numbers of image pairs across varied light positions, colors, and intensities while keeping the scene content consistent with the original image. LightMover enables precise, independent control over light position, color, and intensity, and achieves high PSNR and strong semantic consistency (DINO, CLIP) across different tasks.
Read the full abstract

All authors Gengze Zhou, Tianyu Wang, Soo Ye Kim, Zhixin Shu, Xin Yu, Yannick Hold-Geoffroy, Sumit Chaturvedi, Qi Wu, Zhe Lin, Scott Cohen