Peer Revenue Impact factor: volatile

Papers

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

Computer Science Computation and Language

cs.CL Watch Computation and Language

Wednesday 29 October

Computation and Language

Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs

Alexander Sternfeld, Andrei Kucharavy, Dimitri Percia David et al. (+3 more)

Forecasting transformative technologies remains a critical but challenging task, particularly in fast-evolving domains such as Information and Communication Technologies (ICTs). Traditional expert-based methods struggle to keep pace with short innovation cycles and ambiguous early-stage terminology. In this work, we propose a novel, data-driven pipeline to monitor the emergence of transformative technologies by identifying patterns of technological convergence. Our approach leverages advances in Large Language Models (LLMs) to extract semantic triples from unstructured text and construct a large-scale graph of technology-related entities and relations. We introduce a new method for grouping semantically similar technology terms (noun stapling) and develop graph-based metrics to detect convergence signals. The pipeline includes multi-stage filtering, domain-specific keyword clustering, and a temporal trend analysis of topic co-occurence. We validate our methodology on two complementary datasets: 278,625 arXiv preprints (2017–2024) to capture early scientific signals, and 9,793 USPTO patent applications (2018-2024) to track downstream commercial developments. Our results demonstrate that the proposed pipeline can identify both established and emerging convergence patterns, offering a scalable and generalizable framework for technology forecasting grounded in full-text analysis.
Read the full abstract

All authors Alexander Sternfeld, Andrei Kucharavy, Dimitri Percia David, Alain Mermoud, Julian Jang-Jaccard, Nathan Monnet

Computation and Language

CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs

Luca Capone, Alessandro Bondielli and Alessandro Lenci

This work investigates whether small-scale LMs can benefit from instruction tuning. We compare conversational and question-answering instruction tuning datasets, applied either in a merged or sequential curriculum, using decoder-only models with 100M and 140M parameters. Evaluation spans both fine-tuning (SuperGLUE) and zero-shot (BLiMP, EWoK, WUGs, entity tracking, and psycholinguistic correlation) settings. Results show that instruction tuning yields small but consistent gains in fine-tuning scenarios, with sequential curricula outperforming merged data; however, improvements do not consistently transfer to zero-shot tasks, suggesting a trade-off between interaction-focused adaptation and broad linguistic generalization. These results highlight both the potential and the constraints of adapting human-inspired learning strategies to low-resource LMs, and point toward hybrid, curriculum-based approaches for enhancing generalization under ecological training limits.
Read the full abstract

Computation and Language

Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysis

Abhishek Purushothama, Junghyun Min, Brandon Waldon et al. (+1 more)

In the U.S. judicial system, a widespread approach to legal interpretation entails assessing how a legal text would be understood by an `ordinary' speaker of the language. Recent scholarship has proposed that legal practitioners leverage large language models (LLMs) to ascertain a text's ordinary meaning. But are LLMs up to the task? As textual interpretation questions arise in spheres ranging from criminal law to civil rights, we argue it is crucial that models not be taken as authoritative without rigorous evaluation. This work offers an empirical argument against LLM-assisted interpretation as recently practiced by legal scholars and federal judges, who reasoned the large amount of data that models see in training would enable models to illuminate how people ordinarily use certain words or phrases. In controlled experiments, we find failures in robustness which cast doubt on this assumption and raise serious questions about the utility of these models in practice. For the models in our evaluation, slight changes to the format of a question can lead to wildly different conclusions – a vulnerability that parties with an interest in the outcome could exploit. Comparing with a dataset where people were asked similar legal interpretation questions, we see that these models are at best moderately correlated to human judgments – not strong enough given the stakes in this domain.
Read the full abstract

All authors Abhishek Purushothama, Junghyun Min, Brandon Waldon, Nathan Schneider

Computation and Language

CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memories

Yilong Lai, Yipin Yang, Ting Liang et al. (+4 more)

Recent years have witnessed the rapid development of LLM-based agents, which shed light on using language agents to solve complex real-world problems. A prominent application lies in business agents, which interact with databases and internal knowledge bases via tool calls to fulfill diverse user requirements. However, this domain is characterized by intricate data relationships and a wide range of heterogeneous tasks, from statistical data queries to knowledge-based question-answering. To address these challenges, we propose CRMWeaver, a novel approach that enhances business agents in such complex settings. To acclimate the agentic model to intricate business environments, we employ a synthesis data generation and RL-based paradigm during training, which significantly improves the model's ability to handle complex data and varied tasks. During inference, a shared memories mechanism is introduced, prompting the agent to learn from task guidelines in similar problems, thereby further boosting its effectiveness and generalization, especially in unseen scenarios. We validate the efficacy of our approach on the CRMArena-Pro dataset, where our lightweight model achieves competitive results in both B2B and B2C business scenarios, underscoring its practical value for real-world applications.
Read the full abstract

All authors Yilong Lai, Yipin Yang, Ting Liang, Jialong Wu, Zhenglin Wang, Jianguo Lin, Keping Yang

Computation and Language · Cross-listed from cs.AI

GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning

Jiaqi Wu, Qinlao Zhao, Zefeng Chen et al. (+4 more)

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to exploit the inherent parallelism among independent sub-tasks. This sequential bottleneck leads to inefficient tool utilization and suboptimal performance in multi-step reasoning scenarios. We introduce Graph-based Agent Planning (GAP), a novel framework that explicitly models inter-task dependencies through graph-based planning to enable adaptive parallel and serial tool execution. Our approach trains agent foundation models to decompose complex tasks into dependency-aware sub-task graphs, autonomously determining which tools can be executed in parallel and which must follow sequential dependencies. This dependency-aware orchestration achieves substantial improvements in both execution efficiency and task accuracy. To train GAP, we construct a high-quality dataset of graph-based planning traces derived from the Multi-Hop Question Answering (MHQA) benchmark. We employ a two-stage training strategy: supervised fine-tuning (SFT) on the curated dataset, followed by reinforcement learning (RL) with a correctness-based reward function on strategically sampled queries where tool-based reasoning provides maximum value. Experimental results on MHQA datasets demonstrate that GAP significantly outperforms traditional ReAct baselines, particularly on multi-step retrieval tasks, while achieving dramatic improvements in tool invocation efficiency through intelligent parallelization. The project page is available at: https://github.com/WJQ7777/Graph-Agent-Planning.
Read the full abstract

All authors Jiaqi Wu, Qinlao Zhao, Zefeng Chen, Kai Qin, Yifei Zhao, Xueqian Wang, Yuhang Yao

Computation and Language

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning

Senjie Jin, Lu Chen, Zhiheng Xi et al. (+9 more)

Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasoning problems. Current research typically endeavors to achieve unidirectional enhancement: P-CoT enhanced N-CoT or N-CoT enhanced P-CoT. In this paper, we seek to fully unleash the two paradigms' strengths for mutual enhancement and ultimately achieve simultaneous improvements. We conduct a detailed analysis of the error types across two paradigms, based on which we propose Parrot, a novel training pipeline for mathematical problems: 1) Three target-designed subtasks integrate sequential P-CoT and N-CoT generation. 2) A subtask hybrid training strategy to facilitate natural language semantic transferability. 3) The converted N-CoT auxiliary reward is designed to alleviate the sparse rewards in P-CoT optimization. Extensive experiments demonstrate that Parrot significantly enhances both the performance of N-CoT and P-CoT, especially on N-CoT. Using Parrot SFT, the N-CoT performance of LLaMA2 and CodeLLaMA achieve gains of +21.87 and +21.48 on MathQA over the RL baseline, which is resource-intensive.
Read the full abstract

All authors Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang

Computation and Language

Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student

Soumyadeep Jana and Sanasam Ranbir Singh

Multimodal sarcasm detection is challenging, especially in low-resource settings where subtle image-text contradictions are hard to learn due to scarce annotated data, which hinders the model's performance. Parameter-efficient fine-tuning (PEFT) methods like adapters, LoRA, and prompt tuning reduce overfitting but struggle to reach optimal performance due to limited supervision from few-shot data. We propose PEKD, a unified framework that enhances PEFT methods via distillation from an expert model trained on large-scale sarcasm data, which acts as the teacher. To mitigate unreliable signals from the teacher, we introduce an entropy-aware gating mechanism that dynamically adjusts the distillation strength based on teacher confidence. Experiments on two public datasets demonstrate that our PEKD framework enables PEFT methods to outperform both prior parameter-efficient approaches and large multimodal models, achieving strong results in the few-shot scenario. The framework is modular and adaptable to a wide range of multimodal models and tasks.
Read the full abstract

Computation and Language

Adapting Small Language Models to Low-Resource Domains: A Case Study in Hindi Tourism QA

Sandipan Majhi and Paheli Bhattacharya

Domain-specific question answering in low-resource languages faces two key challenges: scarcity of annotated datasets and limited domain knowledge in general-purpose language models. In this work, we present a multi-stage finetuning strategy to adapt lightweight language models to the Hindi tourism domain by leveraging both original and synthetic training data. Synthetic question-answer pairs are generated using large LLMs (LLaMA-70B, Phi-14B) and used to augment the limited original dataset. We explore several training methodologies and analyse their impact on domain generalisation. Our results demonstrate that large models can efficiently generate synthetic data, while small models can effectively adapt to it, offering a scalable pathway for low-resource, domain-specific QA.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity

Tianxi Wan, Jiaming Luo, Siyuan Chen et al. (+4 more)

Psychiatric comorbidity is clinically significant yet challenging due to the complexity of multiple co-occurring disorders. To address this, we develop a novel approach integrating synthetic patient electronic medical record (EMR) construction and multi-agent diagnostic dialogue generation. We create 502 synthetic EMRs for common comorbid conditions using a pipeline that ensures clinical relevance and diversity. Our multi-agent framework transfers the clinical interview protocol into a hierarchical state machine and context tree, supporting over 130 diagnostic states while maintaining clinical standards. Through this rigorous process, we construct PsyCoTalk, the first large-scale dialogue dataset supporting comorbidity, containing 3,000 multi-turn diagnostic dialogues validated by psychiatrists. This dataset enhances diagnostic accuracy and treatment planning, offering a valuable resource for psychiatric comorbidity research. Compared to real-world clinical transcripts, PsyCoTalk exhibits high structural and linguistic fidelity in terms of dialogue length, token distribution, and diagnostic reasoning strategies. Licensed psychiatrists confirm the realism and diagnostic validity of the dialogues. This dataset enables the development and evaluation of models capable of multi-disorder psychiatric screening in a single conversational pass.
Read the full abstract

All authors Tianxi Wan, Jiaming Luo, Siyuan Chen, Kunyao Lan, Jianhua Chen, Haiyang Geng, Mengyue Wu

Computation and Language

ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation

Ziyi Liu, Bahar Sarrafzadeh, Pei Zhou et al. (+3 more)

While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that can proactively manage complex, multi-party collaboration. Systematic evaluation methods for such proactive agents remain scarce, limiting progress in developing AI that can effectively support multiple people together. Negotiation offers a demanding testbed for this challenge, requiring socio-cognitive intelligence to navigate conflicting interests between multiple participants and multiple topics and build consensus. Here, we present ProMediate, the first framework for evaluating proactive AI mediator agents in complex, multi-topic, multi-party negotiations. ProMediate consists of two core components: (i) a simulation testbed based on realistic negotiation cases and theory-driven difficulty levels (ProMediate-Easy, ProMediate-Medium, and ProMediate-Hard), with a plug-and-play proactive AI mediator grounded in socio-cognitive mediation theories, capable of flexibly deciding when and how to intervene; and (ii) a socio-cognitive evaluation framework with a new suite of metrics to measure consensus changes, intervention latency, mediator effectiveness, and intelligence. Together, these components establish a systematic framework for assessing the socio-cognitive intelligence of proactive AI agents in multi-party settings. Our results show that a socially intelligent mediator agent outperforms a generic baseline, via faster, better-targeted interventions. In the ProMediate-Hard setting, our social mediator increases consensus change by 3.6 percentage points compared to the generic baseline (10.65% vs 7.01%) while being 77% faster in response (15.98s vs. 3.71s). In conclusion, ProMediate provides a rigorous, theory-grounded testbed to advance the development of proactive, socially intelligent agents.
Read the full abstract

All authors Ziyi Liu, Bahar Sarrafzadeh, Pei Zhou, Longqi Yang, Jieyu Zhao, Ashish Sharma

Computation and Language · Cross-listed from cs.AI

RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models

Tianqianjin Lin, Xi Zhao, Xingyao Zhang et al. (+5 more)

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For tasks beyond the LLM's current competence, such reasoning path can be hard to sample, and learning risks reinforcing familiar but suboptimal reasoning. We are motivated by the insight from cognitive science that Why is this the answer is often an easier question than What is the answer, as it avoids the heavy cognitive load of open-ended exploration, opting instead for explanatory reconstruction-systematically retracing the reasoning that links a question to its answer. We show that LLMs can similarly leverage answers to derive high-quality reasoning paths. We formalize this phenomenon and prove that conditioning on answer provably increases the expected utility of sampled reasoning paths, thereby transforming intractable problems into learnable ones. Building on this insight, we introduce RAVR (Reference-Answer-guided Variational Reasoning), an end-to-end framework that uses answer-conditioned reasoning as a variational surrogate for question-only reasoning. Experiments in both general and math domains demonstrate consistent improvements over strong baselines. We further analyze the reasoning behavior and find that RAVR reduces hesitation, strengthens conclusion consolidation, and promotes problem-specific strategies in reasoning.
Read the full abstract

All authors Tianqianjin Lin, Xi Zhao, Xingyao Zhang, Rujiao Long, Yi Xu, Zhuoren Jiang, Wenbo Su, Bo Zheng

Computation and Language

Testing Cross-Lingual Text Comprehension In LLMs Using Next Sentence Prediction

Ritesh Sunil Chavan and Jack Mostow

While large language models are trained on massive datasets, this data is heavily skewed towards English. Does their impressive performance reflect genuine ability or just this data advantage? To find out, we tested them in a setting where they could not rely on data abundance: low-resource languages. Building on prior work Agarwal et al. (2025) that used Next Sentence Prediction (NSP) as a test, we created a large-scale benchmark with 10,000 questions each for English (a high-resource language), Swahili (medium-resource), and Hausa (low-resource). We then tested several top models, including GPT-4 Turbo, Gemini 1.5 Flash, and LLaMA 3 70B, to see how their performance holds up. The results painted a clear picture of how levels of language resources impact outcomes. While all models excelled in English, their accuracy dropped in Swahili and fell sharply in Hausa, with LLaMA 3 struggling the most. The story became even more interesting when we introduced Chain-of-Thought (CoT) prompting. For the struggling LLaMA 3, CoT acted as a helpful guide, significantly boosting its accuracy. However, for the more capable GPT-4 and Gemini, the same technique often backfired, leading to a kind of "overthinking" that hurt their results in the cross-lingual context. This reveals that Chain-of-Thought is not a universal solution; its effectiveness depends heavily on the model's baseline capability and the specific context of the task. Our framework pinpoints LLM weaknesses, highlights when CoT helps or hinders cross-lingual NSP performance, and factors influencing their decisions.
Read the full abstract

Computation and Language

Model-Document Protocol for AI Search

Hongjin Qian and Zheng Liu

AI search depends on linking large language models (LLMs) with vast external knowledge sources. Yet web pages, PDF files, and other raw documents are not inherently LLM-ready: they are long, noisy, and unstructured. Conventional retrieval methods treat these documents as verbatim text and return raw passages, leaving the burden of fragment assembly and contextual reasoning to the LLM. This gap underscores the need for a new retrieval paradigm that redefines how models interact with documents. We introduce the Model-Document Protocol (MDP), a general framework that formalizes how raw text is bridged to LLMs through consumable knowledge representations. Rather than treating retrieval as passage fetching, MDP defines multiple pathways that transform unstructured documents into task-specific, LLM-ready inputs. These include agentic reasoning, which curates raw evidence into coherent context; memory grounding, which accumulates reusable notes to enrich reasoning; and structured leveraging, which encodes documents into formal representations such as graphs or key-value caches. All three pathways share the same goal: ensuring that what reaches the LLM is not raw fragments but compact, structured knowledge directly consumable for reasoning. As an instantiation, we present MDP-Agent, which realizes the protocol through an agentic process: constructing document-level gist memories for global coverage, performing diffusion-based exploration with vertical exploitation to uncover layered dependencies, and applying map-reduce style synthesis to integrate large-scale evidence into compact yet sufficient context. Experiments on information-seeking benchmarks demonstrate that MDP-Agent outperforms baselines, validating both the soundness of the MDP framework and the effectiveness of its agentic instantiation.
Read the full abstract

Computation and Language

Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR

Shreyas Gopal, Ashutosh Anshul, Haoyang Li et al. (+3 more)

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works that quantize Whisper embeddings for speech-to-unit modeling, we propose disentangling semantic speech content from background noise in the latent space. Our end-to-end model separates clean speech in the form of codebook tokens, while extracting interpretable noise vectors as quantization residue which are supervised via a lightweight classifier. We show that our approach improves alignment between clean/noisy speech and text, producing speech tokens that display a high degree of noiseinvariance, and improves ASR performance. Keeping Whisper frozen, we show an 82% reduction in error rate compared to Whisper, and 35% improvement over baseline methods on the VBDemand test set. Further analyses show that the learned token space generalizes well to both seen and unseen acoustic conditions.
Read the full abstract

All authors Shreyas Gopal, Ashutosh Anshul, Haoyang Li, Yue Heng Yeo, Hexin Liu, Eng Siong Chng

Computation and Language

A Survey on Unlearning in Large Language Models

Ruichen Qiu, Jiajun Tan, Jiayue Pu et al. (+3 more)

Large Language Models (LLMs) demonstrate remarkable capabilities, but their training on massive corpora poses significant risks from memorized sensitive information. To mitigate these issues and align with legal standards, unlearning has emerged as a critical technique to selectively erase specific knowledge from LLMs without compromising their overall performance. This survey provides a systematic review of over 180 papers on LLM unlearning published since 2021. First, it introduces a novel taxonomy that categorizes unlearning methods based on the phase in the LLM pipeline of the intervention. This framework further distinguishes between parameter modification and parameter selection strategies, thus enabling deeper insights and more informed comparative analysis. Second, it offers a multidimensional analysis of evaluation paradigms. For datasets, we compare 18 existing benchmarks from the perspectives of task format, content, and experimental paradigms to offer actionable guidance. For metrics, we move beyond mere enumeration by dividing knowledge memorization metrics into 10 categories to analyze their advantages and applicability, while also reviewing metrics for model utility, robustness, and efficiency. By discussing current challenges and future directions, this survey aims to advance the field of LLM unlearning and the development of secure AI systems.
Read the full abstract

All authors Ruichen Qiu, Jiajun Tan, Jiayue Pu, Honglin Wang, Xiao-Shan Gao, Fei Sun

Computation and Language

Pretraining Strategies using Monolingual and Parallel Data for Low-Resource Machine Translation

Idriss Nguepi Nguefack, Mara Finkelstein and Toadoum Sari Sakayo

This research article examines the effectiveness of various pretraining strategies for developing machine translation models tailored to low-resource languages. Although this work considers several low-resource languages, including Afrikaans, Swahili, and Zulu, the translation model is specifically developed for Lingala, an under-resourced African language, building upon the pretraining approach introduced by Reid and Artetxe (2021), originally designed for high-resource languages. Through a series of comprehensive experiments, we explore different pretraining methodologies, including the integration of multiple languages and the use of both monolingual and parallel data during the pretraining phase. Our findings indicate that pretraining on multiple languages and leveraging both monolingual and parallel data significantly enhance translation quality. This study offers valuable insights into effective pretraining strategies for low-resource machine translation, helping to bridge the performance gap between high-resource and low-resource languages. The results contribute to the broader goal of developing more inclusive and accurate NLP models for marginalized communities and underrepresented populations. The code and datasets used in this study are publicly available to facilitate further research and ensure reproducibility, with the exception of certain data that may no longer be accessible due to changes in public availability.
Read the full abstract

Computation and Language

DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai et al. (+9 more)

Modeling opinion change through social interactions is important for understanding polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior (e.g., premature convergence) and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages and private Likert-scale beliefs from U.S.-based participants across 107 topics; the cleaned benchmark used in our experiments contains 2,788 participants in 697 groups, enabling evaluation at the utterance and group levels. We instantiate digital-twin RPLAs with seven LLMs and evaluate across two settings: next-message prediction and full dynamics simulation, using stance-based opinion-dynamics metrics. In zero-shot settings, RPLA groups exhibit strong opinion convergence relative to human groups. Across group-generalization tests with unseen participant groups and topic-generalization tests with unseen discussion topics, supervised fine-tuning (SFT) for Llama-3.1-8B-Instruct improves stance prediction of individuals and convergence prediction at the group level, though discrepancies in opinion change and belief updating remain. The dataset and benchmark website are publicly available.
Read the full abstract

All authors Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai, You Li, Smit Vasani, Binwei Yao, Michael Henry Tessler, Sijia Yang, Dhavan Shah, Robert Hawkins, Junjie Hu, Timothy T. Rogers

Computation and Language · Cross-listed from cs.AI

KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA

Zhuo Chen, Fei Wang, Zixuan Li et al. (+6 more)

Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB). Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Models (LLMs) iteratively decompose a question, generate its corresponding logical queries, and interact with the KB to derive the answer. However, these methods typically fine-tune LLMs on reasoning trajectories synthesized via process supervision, which offers weak incentives for exploration and thus fails to strengthen the agentic reasoning ability. In this paper, we propose KnowCoder-A1, an LLM that can autonomously perform agentic reasoning on KBs to obtain answers. To incentivize autonomous exploration, KnowCoder-A1 trains the LLM under outcome-only supervision via a multi-stage curriculum reinforcement learning with an easy-to-hard curriculum. To establish foundational agentic capabilities, KnowCoder-A1 first fine-tunes the LLM on a small set of high-quality trajectories obtained through outcome-based rejection sampling. Then, to alleviate the reward sparsity inherent in outcome-only supervision, it applies multi-stage curriculum RL with reward schedules that progress from easy to hard. Trained with outcome-only supervision, KnowCoder-A1 exhibits powerful reasoning behaviors and consistently outperforms prior approaches across three mainstream datasets. Notably, on the zero-shot subset of GrailQA, KnowCoder-A1 achieves up to an 11.1% relative improvement while using only one-twelfth of the training data, demonstrating strong agentic reasoning capabilities.
Read the full abstract

All authors Zhuo Chen, Fei Wang, Zixuan Li, Zhao Zhang, Weiwei Ding, Chuanguang Yang, Yongjun Xu, Xiaolong Jin, Jiafeng Guo

Computation and Language

BioCoref: Benchmarking Biomedical Coreference Resolution with LLMs

Nourah M Salem, Elizabeth White, Michael Bada et al. (+1 more)

Coreference resolution in biomedical texts presents unique challenges due to complex domain-specific terminology, high ambiguity in mention forms, and long-distance dependencies between coreferring expressions. In this work, we present a comprehensive evaluation of generative large language models (LLMs) for coreference resolution in the biomedical domain. Using the CRAFT corpus as our benchmark, we assess the LLMs' performance with four prompting experiments that vary in their use of local, contextual enrichment, and domain-specific cues such as abbreviations and entity dictionaries. We benchmark these approaches against a discriminative span-based encoder, SpanBERT, to compare the efficacy of generative versus discriminative methods. Our results demonstrate that while LLMs exhibit strong surface-level coreference capabilities, especially when supplemented with domain-grounding prompts, their performance remains sensitive to long-range context and mentions ambiguity. Notably, the LLaMA 8B and 17B models show superior precision and F1 scores under entity-augmented prompting, highlighting the potential of lightweight prompt engineering for enhancing LLM utility in biomedical NLP tasks.
Read the full abstract

All authors Nourah M Salem, Elizabeth White, Michael Bada, Lawrence Hunter

Computation and Language

TOPol: Reconstructing and Interpreting Multidimensional Semantic Polarity Fields

Lucia Gomez, Gabin Taibi and Julius Sipke Kooistra

Polarity in natural language processing has long been operationalized as a single axis: the sentiment construct. We challenge this one-dimensional view by asking what a topic's documents are bipolar about, without specifying an answer in advance. TOPol inverts the usual concept-direction paradigm: rather than mapping a named construct to one direction, it maps a topic to the full set of statistically reproducible bipolar semantic axes its documents support in a transformer's residual stream, and asks only afterwards which of them correspond to a known construct. These axes need not be evaluative. The method is a recursive, orthogonal-by-construction bipartition of each topic's document cloud, with a candidate axis promoted to a finding only if it survives one pre-specified split-half stability gate. We calibrate against a known answer first: on 9,986 Amazon reviews (14 discovered topics) in Gemma 3 4B, the star-rating difference-in-means vector serves as a ruler known by construction to be sentiment. Discovery blindly re-derives the sentiment axis in every topic (cosine 0.71-0.97) without ever seeing the rating label, while the same gate certifies 543 axes, of which 106 are near-orthogonal to sentiment yet equally reproducible; each topic supports 33-45 mutually orthogonal axes, and sentiment axes resolve in later layers than the rest. Differential vocabulary, an internals-grounded natural-language decoder and vocabulary-based clustering agree on what the non-sentiment axes contrast; clustering by shared vocabulary surfaces 99 families, 9 recurring across topics. Direction similarity to the ruler predicts an independent sentiment estimate only weakly ($r=0.243$). Polarity is better treated as a property of a topic's representational geometry, with a measurable rank and a per-axis depth, than as one universal scalar.
Read the full abstract

Computation and Language

Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?

Seonjeong Hwang, Hyounghun Kim and Gary Geunbae Lee

Estimating the cognitive complexity of reading comprehension (RC) items is crucial for assessing item difficulty before it is administered to learners. Unlike syntactic and semantic features, such as passage length or semantic similarity between options, cognitive features that arise during answer reasoning are not readily extractable using existing NLP tools and have traditionally relied on human annotation. In this study, we examine whether large language models (LLMs) can estimate the cognitive complexity of RC items by focusing on two dimensions-Evidence Scope and Transformation Level-that indicate the degree of cognitive burden involved in reasoning about the answer. Our experimental results demonstrate that LLMs can approximate the cognitive complexity of items, indicating their potential as tools for prior difficulty analysis. Further analysis reveals a gap between LLMs' reasoning ability and their metacognitive awareness: even when they produce correct answers, they sometimes fail to correctly identify the features underlying their own reasoning process.
Read the full abstract

Computation and Language

GAPMAP: Mapping Scientific Knowledge Gaps in Biomedical Literature Using Large Language Models

Nourah M Salem, Elizabeth White, Michael Bada et al. (+1 more)

Scientific progress is driven by the deliberate articulation of what remains unknown. This study investigates the ability of large language models (LLMs) to identify research knowledge gaps in the biomedical literature. We define two categories of knowledge gaps: explicit gaps, clear declarations of missing knowledge; and implicit gaps, context-inferred missing knowledge. While prior work has focused mainly on explicit gap detection, we extend this line of research by addressing the novel task of inferring implicit gaps. We conducted two experiments on almost 1500 documents across four datasets, including a manually annotated corpus of biomedical articles. We benchmarked both closed-weight models (from OpenAI) and open-weight models (Llama and Gemma 2) under paragraph-level and full-paper settings. To address the reasoning of implicit gaps inference, we introduce \small TABI, a Toulmin-Abductive Bucketed Inference scheme that structures reasoning and buckets inferred conclusion candidates for validation. Our results highlight the robust capability of LLMs in identifying both explicit and implicit knowledge gaps. This is true for both open- and closed-weight models, with larger variants often performing better. This suggests a strong ability of LLMs for systematically identifying candidate knowledge gaps, which can support early-stage research formulation, policymakers, and funding decisions. We also report observed failure modes and outline directions for robust deployment, including domain adaptation, human-in-the-loop verification, and benchmarking across open- and closed-weight models.
Read the full abstract

All authors Nourah M Salem, Elizabeth White, Michael Bada, Lawrence Hunter

Computation and Language

Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech

Pedro Corrêa, João Lima, Victor Moreno et al. (+2 more)

Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks. Although promising results have been achieved, there is growing discussion regarding these models' generalization capabilities and the extent to which they truly integrate audio and text modalities in their internal representations. In this work, we evaluate four SLMs on the task of speech emotion recognition using a dataset of emotionally incongruent speech samples, a condition under which the semantic content of the spoken utterance conveys one emotion while speech expressiveness conveys another. Our results indicate that SLMs rely predominantly on textual semantics rather than speech emotion to perform the task, indicating that text-related representations largely dominate over acoustic representations. We release both the code and the Emotionally Incongruent Synthetic Speech dataset (EMIS) to the community.
Read the full abstract

All authors Pedro Corrêa, João Lima, Victor Moreno, Lucas Ueda, Paula Dornhofer Paro Costa

Tuesday 28 October

Computation and Language

Where did you get that? Towards Summarization Attribution for Analysts

Violet B, John M. Conroy, Sean Lynch et al. (+4 more)

Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.
Read the full abstract

All authors Violet B, John M. Conroy, Sean Lynch, Danielle M, Neil P. Molino, Aaron Wiechmann, Julia S. Yang

Computation and Language

SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection

Jingqing Wang, Jiaxing Shang, Rong Xu et al. (+3 more)

Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.
Read the full abstract

All authors Jingqing Wang, Jiaxing Shang, Rong Xu, Fei Hao, Tianjin Huang, Geyong Min

Computation and Language · Cross-listed from cs.SD

A Penny for Your Thoughts: Decoding Speech from Inexpensive Brain Signals

Quentin Auster, Kateryna Shapovalenko, Chuang Ma et al. (+1 more)

We explore whether neural networks can decode brain activity into speech by mapping EEG recordings to audio representations. Using EEG data recorded as subjects listened to natural speech, we train a model with a contrastive CLIP loss to align EEG-derived embeddings with embeddings from a pre-trained transformer-based speech model. Building on the state-of-the-art EEG decoder from Meta, we introduce three architectural modifications: (i) subject-specific attention layers (+0.15% WER improvement), (ii) personalized spatial attention (+0.45%), and (iii) a dual-path RNN with attention (-1.87%). Two of the three modifications improved performance, highlighting the promise of personalized architectures for brain-to-speech decoding and applications in brain-computer interfaces.
Read the full abstract

All authors Quentin Auster, Kateryna Shapovalenko, Chuang Ma, Demaio Sun

Computation and Language

BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection

Yaniv Nikankin, Dana Arad, Itay Itzhak et al. (+4 more)

One of the main challenges in mechanistic interpretability is circuit discovery, determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield more faithful circuits and outperform prior approaches across multiple MIB tasks and models. Our code is available at: https://github.com/technion-cs-nlp/MIB-Shared-Task.
Read the full abstract

All authors Yaniv Nikankin, Dana Arad, Itay Itzhak, Anja Reusch, Adi Simhi, Gal Kesten-Pomeranz, Yonatan Belinkov

Computation and Language

zFLoRA: Zero-Latency Fused Low-Rank Adapters

Dhananjaya Gowda, Seoha Song, Harshith Goka et al. (+1 more)

Large language models (LLMs) are increasingly deployed with task-specific adapters catering to multiple downstream applications. In such a scenario, the additional compute associated with these apparently insignificant number of adapter parameters (typically less than 1% of the base model) turns out to be disproportionately significant during inference time (upto 2.5x times that of the base model). In this paper, we propose a new zero-latency fused low-rank adapter (zFLoRA) that introduces zero or negligible latency overhead on top of the base model. Experimental results on LLMs of size 1B, 3B and 7B show that zFLoRA compares favorably against the popular supervised fine-tuning benchmarks including low-rank adapters (LoRA) as well as full fine-tuning (FFT). Experiments are conducted on 18 different tasks across three different categories namely commonsense reasoning, math reasoning and summary-dialogue. Latency measurements made on NPU (Samsung Galaxy S25+) as well as GPU (NVIDIA H100) platforms show that the proposed zFLoRA adapters introduce zero to negligible latency overhead.
Read the full abstract

All authors Dhananjaya Gowda, Seoha Song, Harshith Goka, Junhyun Lee

Computation and Language

LASTIST: LArge-Scale Target-Independent STance dataset

DongJae Kim, Yaejin Lee, Minsu Park et al. (+1 more)

Stance detection has emerged as an area of research in the field of artificial intelligence. However, most research is currently centered on the target-dependent stance detection task, which is based on a person's stance in favor of or against a specific target. Furthermore, most benchmark datasets are based on English, making it difficult to develop models in low-resource languages such as Korean, especially for an emerging field such as stance detection. This study proposes the LArge-Scale Target-Independent STance (LASTIST) dataset to fill this research gap. Collected from the press releases of both parties on Korean political parties, the LASTIST dataset uses 563,299 labeled Korean sentences. We provide a detailed description of how we collected and constructed the dataset and trained state-of-the-art deep learning and stance detection models. Our LASTIST dataset is designed for various tasks in stance detection, including target-independent stance detection and diachronic evolution stance detection. We deploy our dataset on https://anonymous.4open.science/r/LASTIST-3721/.
Read the full abstract

All authors DongJae Kim, Yaejin Lee, Minsu Park, Eunil Park

Computation and Language · Cross-listed from cs.DB

StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems

Qi Lin, Zhenyu Zhang, Viraj Thakkar et al. (+3 more)

Automatically configuring storage systems is hard: parameter spaces are large and conditions vary across workloads, deployments, and versions. Heuristic and ML tuners are often system specific, require manual glue, and degrade under changes. Recent LLM-based approaches help but usually treat tuning as a single-shot, system-specific task, which limits cross-system reuse, constrains exploration, and weakens validation. We present StorageXTuner, an LLM agent-driven auto-tuning framework for heterogeneous storage engines. StorageXTuner separates concerns across four agents - Executor (sandboxed benchmarking), Extractor (performance digest), Searcher (insight-guided configuration exploration), and Reflector (insight generation and management). The design couples an insight-driven tree search with layered memory that promotes empirically validated insights and employs lightweight checkers to guard against unsafe actions. We implement a prototype and evaluate it on RocksDB, LevelDB, CacheLib, and MySQL InnoDB with YCSB, MixGraph, and TPC-H/C. Relative to out-of-the-box settings and to ELMo-Tune, StorageXTuner reaches up to 575% and 111% higher throughput, reduces p99 latency by as much as 88% and 56%, and converges with fewer trials.
Read the full abstract

All authors Qi Lin, Zhenyu Zhang, Viraj Thakkar, Zhenjie Sun, Mai Zheng, Zhichao Cao