Computation and Language · Cross-listed from cs.CE
AI-Driven Modular Services for Accessible Multilingual Education in Immersive Extended Reality Settings: Integrating Speech Processing, Translation, and Sign Language Rendering
N.D. Tantaroudas, A.J. McCracken, I. Karachalios et al. (+1 more)
This work introduces a modular platform that brings together six AI services, automatic
speech recognition via OpenAI Whisper,
multilingual translation through Meta NLLB,
speech synthesis using AWS Polly,
emotion classification with RoBERTa, dialogue summarisation via flan t5 base samsum, and International Sign (IS) rendering through Google MediaPipe. A corpus of IS gesture recordings was processed to derive hand landmark coordinates, which were subsequently mapped onto three dimensional avatar animations inside a virtual reality (VR) environment. Validation comprised technical benchmarking of each AI component, including comparative assessments of
speech synthesis providers and
multilingual translation models (NLLB 200 and EuroLLM 1.7B variants). Technical evaluations confirmed the suitability of the platform for real time XR deployment.
Speech synthesis benchmarking established that AWS Polly delivers the lowest latency at a competitive price point. The EuroLLM 1.7B Instruct variant attained a higher BLEU score, surpassing NLLB. These findings establish the viability of orchestrating cross modal AI services within XR settings for accessible,
multilingual language instruction. The modular design permits independent scaling and adaptation to varied educational contexts, providing a foundation for equitable learning solutions aligned with European Union digital accessibility goals.
Read the full abstract ▾
All authors N.D. Tantaroudas, A.J. McCracken, I. Karachalios, E. Papatheou
Computation and Language
THIVLVC: Retrieval Augmented Dependency Parsing for Latin
Luc Pommeret, Thibault Wagret and Jules Deret
We describe THIVLVC, a two-stage system for the EvaLatin 2026 Dependency Parsing task. Given a Latin sentence, we retrieve structurally similar entries from the CIRCSE treebank using sentence length and POS n-gram similarity, then
prompt a large
language model to refine the baseline parse from UDPipe using the retrieved examples and UD annotation guidelines. We submit two configurations: one without
retrieval and one with
retrieval (RAG). On poetry (Seneca), THIVLVC improves CLAS by +17 points over the UDPipe baseline; on prose (Thomas Aquinas), the gain is +1.5 CLAS. A double-blind error analysis of 300 divergences between our system and the gold standard reveals that, among unanimous annotator decisions, 53.3% favour THIVLVC, showing annotation inconsistencies both within and across treebanks.
Read the full abstract ▾
Computation and Language
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
Xuan Dong, Huanyang Zheng, Tianhao Niu et al. (+7 more)
Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across papers to align experimental settings and support reproducible conclusions. This joint capability is not systematically assessed in existing
benchmarks, which largely under-evaluate proactive search, multi-evidence integration and sustained evidence use over time. In this work, we introduce EpiBench, an episodic multi-turn
multimodal benchmark that instantiates short research workflows. Given a research task,
agents must navigate across papers over multiple turns, align evidence from figures and tables, and use the accumulated evidence in the
memory to answer objective questions that require cross paper comparisons and multi-figure integration. EpiBench introduces a process-level evaluation framework for fine-grained testing and diagnosis of research
agents. Our experiments show that even the leading model achieves an accuracy of only 29.23% on the hard split, indicating substantial room for improvement in multi-turn, multi-evidence research workflows, providing an evaluation platform for verifiable and reproducible research
agents.
Read the full abstract ▾
All authors Xuan Dong, Huanyang Zheng, Tianhao Niu, Zhe Han, Pengzhan Li, Bofei Liu, Zhengyang Liu, Guancheng Li, Qingfu Zhu, Wanxiang Che
Computation and Language
Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue
Junan Hu, Shudan Guo, Wenqi Liu et al. (+2 more)
Large
Language Models demonstrate outstanding performance in many
language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The prevalent approach of treating dialogue history as a flat, linear sequence is misaligned with the intrinsically hierarchical and branching structure of natural discourse, leading to inefficient context utilization and a loss of coherence during extended interactions involving topic shifts or instruction refinements. To address this limitation, we introduce Context-
Agent, a novel framework that models multi-turn dialogue history as a dynamic tree structure. This approach mirrors the inherent non-linearity of conversation, enabling the model to maintain and navigate multiple dialogue branches corresponding to different topics. Furthermore, to facilitate robust evaluation, we introduce the Non-linear Task Multi-turn Dialogue (NTM)
benchmark, specifically designed to assess model performance in long-horizon, non-linear scenarios. Our experiments demonstrate that Context-
Agent enhances task completion rates and improves
token efficiency across various LLMs, underscoring the value of structured context management for complex, dynamic dialogues. The
dataset and code is available at GitHub.
Read the full abstract ▾
All authors Junan Hu, Shudan Guo, Wenqi Liu, Jianhua Yin, Yinwei Wei
Computation and Language
FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation–Full Version
Dat Nguyen-Cong, Tung Kieu and Hoang Thanh-Tung
Self-conditioning has been central to the success of continuous
diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where
diffusion is most attractive for deployment: few-step sampling for fast inference. In this study, we show that when models only have a few denoising steps, inaccurate self-conditioning induces a substantial approximation gap; this mistake compounds across denoising steps and ultimately dominate the sample quality. To address this, we propose a novel training framework that handles these errors during learning by perturbing the self-conditioning signal to match inference noise, improving robustness to prior estimation errors. In addition, we introduce a
token-level noise-awareness mechanism that prevents training from saturation, hence improving optimization. Extensive experiments across conditional generation
benchmarks demonstrate that our framework surpasses standard continuous
diffusion models while providing up to 400x faster inference speed, and remains competitive against other one-step
diffusion frameworks.
Read the full abstract ▾
Computation and Language
AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
Yu Li, Chenyang Shao, Xinyang Liu et al. (+13 more)
Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-The-Art (SOTA) performance, creating a growing need for systems that can accelerate the full pipeline of empirical model optimization. In this work, we introduce AutoSOTA, an end-to-end automated research system that advances the latest SOTA models published in top-tier AI papers to reproducible and empirically improved new SOTA models. We formulate this problem through three tightly coupled stages: resource preparation and goal setting; experiment evaluation; and reflection and ideation. To tackle this problem, AutoSOTA adopts a multi-
agent architecture with eight specialized
agents that collaboratively ground papers to code and dependencies, initialize and repair execution environments, track long-horizon experiments, generate and schedule optimization ideas, and supervise validity to avoid spurious gains. We evaluate AutoSOTA on recent research papers collected from eight top-tier AI conferences under filters for code availability and execution cost. Across these papers, AutoSOTA achieves strong end-to-end performance in both automated replication and subsequent optimization. Specifically, it successfully discovers 105 new SOTA models that surpass the original reported methods, averaging approximately five hours per paper. Case studies spanning LLM, NLP, computer
vision, time series, and optimization further show that the system can move beyond routine hyperparameter tuning to identify architectural innovation, algorithmic redesigns, and workflow-level improvements. These results suggest that end-to-end research automation can serve not only as a performance optimizer, but also as a new form of research infrastructure that reduces repetitive experimental burden and helps redirect human
attention toward higher-level scientific creativity.
Read the full abstract ▾
All authors Yu Li, Chenyang Shao, Xinyang Liu, Ruotong Zhao, Peijie Liu, Hongyuan Su, Zhibin Chen, Qinglong Yang, Anjie Xu, Yi Fang, Qingbin Zeng, Tianxing Li, Jingbo Xu, Fengli Xu, Yong Li, Tie-Yan Liu
Computation and Language
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
Yanxu Mao, Peipei Liu, Tiehan Cui et al. (+3 more)
With the widespread application of LLM-based
agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user
prompts, which lack adaptability to new data and may impact the
agent's performance. To address the challenge, this paper proposes the JailAgent framework, which completely avoids modifying the user
prompt. Specifically, it implicitly manipulates the
agent's
reasoning trajectory and
memory retrieval with three key stages: Trigger Extraction,
Reasoning Hijacking, and Constraint Tightening. Through precise trigger identification, real-time adaptive mechanisms, and an optimized objective function, JailAgent demonstrates outstanding performance in cross-model and cross-scenario environments.
Read the full abstract ▾
All authors Yanxu Mao, Peipei Liu, Tiehan Cui, Congying Liu, Mingzhe Xing, Datao You
Computation and Language
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
Jun Zhang, Yicheng Ji, Feiyang Ren et al. (+7 more)
Large
Vision-
Language Models (LVLMs) enable sophisticated
reasoning over images and
videos, yet their inference is hindered by a systemic efficiency barrier known as visual
token dominance. This overhead is driven by a multi-regime interplay between high-resolution feature extraction, quadratic
attention scaling, and
memory bandwidth constraints. We present a systematic taxonomy of efficiency techniques structured around the inference lifecycle, consisting of encoding, prefilling, and decoding. Unlike prior reviews focused on isolated optimizations, we analyze the end-to-end pipeline to reveal how upstream decisions dictate downstream bottlenecks, covering compute-bound visual encoding, the intensive prefilling of massive contexts, and the ”visual
memory wall” in bandwidth-bound decoding. By decoupling the efficiency landscape into the axes of shaping information density, managing long-context
attention, and overcoming
memory limits, this work provides a structured analysis of how isolated optimizations compose to navigate the trade-off between visual fidelity and system efficiency. The survey concludes by outlining four future frontiers supported by pilot empirical insights, including hybrid compression based on functional unit sensitivity, modality-aware decoding with relaxed verification, progressive state management for streaming continuity, and stage-disaggregated serving through hardware-
algorithm co-design. Our literature repository is at https://github.com/SuDIS-ZJU/Efficient-LVLMs-Inference.
Read the full abstract ▾
All authors Jun Zhang, Yicheng Ji, Feiyang Ren, Yihang Li, Bowen Zeng, Zonghao Chen, Ke Chen, Lidan Shou, Gang Chen, Huan Li
Computation and Language
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting
Jinhu Fu, Yan Bai, Longzhu He et al. (+4 more)
Large
language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical problems. (II) Narrow scope: Current methods focus primarily on structured fact triples, overlooking the diverse unstructured forms of factual information (e.g., news, articles) prevalent in real-world contexts. To address these challenges, we propose a new paradigm: teaching LLMs to edit knowledge via Chain of Thoughts (CoTs)
reasoning (CoT2Edit). We first leverage
language model
agents for both structured and unstructured edited data to generate CoTs, building high-quality instruction data. The model is then trained to reason over edited knowledge through supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). At inference time, we integrate
Retrieval-Augmented Generation (RAG) to dynamically retrieve relevant edited facts for real-time knowledge editing. Experimental results demonstrate that our method achieves strong generalization across six diverse knowledge editing scenarios with just a single round of training on three open-source
language models. The codes are available at https://github.com/FredJDean/CoT2Edit.
Read the full abstract ▾
All authors Jinhu Fu, Yan Bai, Longzhu He, Yihang Lou, Yanxiao Zhao, Li Sun, Sen Su
Computation and Language
Turbulence-like 5/3 spectral scaling in contextual representations of language as a complex system
Zhongxin Yang, Chun Bao, Yuanwei Bin et al. (+2 more)
Natural
language is a complex system that exhibits robust statistical regularities. Here, we represent text as a trajectory in a high-dimensional
embedding space generated by
transformer-based
language models, and quantify scale-dependent fluctuations along the
token sequence using an
embedding-step signal. Across multiple
languages and corpora, the resulting power spectrum exhibits a robust power law with an exponent close to $5/3$ over an extended frequency range. This scaling is observed consistently in contextual
embeddings from both human-written and AI-generated text, but is absent in static word
embeddings and is disrupted by randomization of
token order. These results show that the observed scaling reflects multiscale, context-dependent organization rather than lexical statistics alone. By analogy with the Kolmogorov spectrum in
turbulence, our findings suggest that semantic information is integrated in a scale-free, self-similar manner across linguistic scales, and provide a quantitative, model-agnostic
benchmark for studying complex structure in
language representations.
Read the full abstract ▾
All authors Zhongxin Yang, Chun Bao, Yuanwei Bin, Xiang I.A. Yang, Shiyi Chen
Computation and Language
Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs
Hongcheng Liu, Yuhao Wang, Zhe Chen et al. (+5 more)
Omni Large
Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios requiring synergistic omni-modal
reasoning. Beyond understanding global
multimodal context, effective
reasoning also hinges on fine-grained cross-modal
alignment, especially identifying shared referents across modalities, yet this aspect has been largely overlooked. To bridge this gap, we formalize the challenge as a cross-modal coreference problem, where a model must localize a referent in a source modality and re-identify it in a target modality. Building on this paradigm, we introduce CrossOmni, a
dataset comprising nine tasks equipped with human-designed
reasoning rationales to evaluate and enhance this capability. Experiments on 13 Omni-LLMs reveal systematic weaknesses in cross-modal coreference, which we attribute to the absence of coreference-aware thinking patterns. To address this, we enhance cross-modal
alignment via two strategies: a training-free In-Context Learning method and a training-based SFT+GRPO framework designed to induce such thinking patterns. Both approaches yield substantial performance gains and generalize effectively to collaborative
reasoning tasks. Overall, our findings highlight cross-modal coreference as a crucial missing piece for advancing robust omni-modal
reasoning.
Read the full abstract ▾
All authors Hongcheng Liu, Yuhao Wang, Zhe Chen, Pingjie Wang, Zhiyuan Zhu, Yixuan Hou, Yanfeng Wang, Yu Wang
Computation and Language · Cross-listed from cs.AI
Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning
Xiaotian Zhou, Di Tang, Xiaofeng Wang et al. (+1 more)
Large
Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no clear understanding of which topics their answers can be trusted. In this research, we introduce a novel
algorithm, named as GMRL-BD, designed to identify the untrustworthy boundaries (in terms of topics) of a given LLM, with black-box access to the LLM and under specific query constraints. Based on a general Knowledge Graph (KG) derived from Wikipedia, our
algorithm incorporates with multiple reinforcement learning
agents to efficiently identify topics (some nodes in KG) where the LLM is likely to generate biased answers. Our experiments demonstrated the efficiency of our
algorithm, which can detect the untrustworthy boundary with just limited queries to the LLM. Additionally, we have released a new
dataset containing popular LLMs including Llama2, Vicuna, Falcon, Qwen2, Gemma2 and Yi-1.5, along with labels indicating the topics on which each LLM is likely to be biased.
Read the full abstract ▾
All authors Xiaotian Zhou, Di Tang, Xiaofeng Wang, Xiaozhong Liu
Computation and Language
Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
Yuzhe Zhang, Xianwei Xue, Xingyong Wu et al. (+8 more)
Autonomous GUI
agents based on
vision-
language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency, rendering delays, and system interruptions, this assumption leads to undetected action failures, repetitive ineffective behaviors, and catastrophic error accumulation. Moreover, learning robust recovery strategies is challenging due to the high cost of online interaction and the lack of real-time feedback in offline
datasets.We propose VeriGUI (Verification-driven GUI
Agent), which explicitly models action outcomes and recovery under noisy environments. VeriGUI introduces a Thinking–Verification–Action–Expectation (TVAE) framework to detect failures and guide corrective
reasoning, and a two-stage training pipeline that combines Robust SFT with synthetic failure trajectories and GRPO with asymmetric verification rewards. We further construct a Robustness
Benchmark based on AndroidControl to evaluate failure recognition and correction. Experiments show that VeriGUI significantly reduces failure loops and improves recovery success while maintaining competitive standard task performance.
Read the full abstract ▾
All authors Yuzhe Zhang, Xianwei Xue, Xingyong Wu, Mengke Chen, Chen Liu, Xinran He, Run Shao, Feiran Liu, Huanmin Xu, Qiutong Pan, Haiwei Wang
Computation and Language · Cross-listed from cs.IR
CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation
Siddharth Jain and Venkat Narayan Vedam
As
language models shift from single-shot answer generation toward multi-step
reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidence-item utility view we study here. We introduce CUE-R, a lightweight intervention-based framework for measuring per-evidence-item operational utility in single-shot RAG using shallow observable
retrieval-use traces. CUE-R perturbs individual evidence items via REMOVE, REPLACE, and DUPLICATE operators, then measures changes along three utility axes (correctness, proxy-based grounding faithfulness, and confidence error) plus a trace-divergence signal. We also outline an operational evidence-role taxonomy for interpreting intervention outcomes. Experiments on HotpotQA and 2WikiMultihopQA with Qwen-3 8B and GPT-5.2 reveal a consistent pattern: REMOVE and REPLACE substantially harm correctness and grounding while producing large trace shifts, whereas DUPLICATE is often answer-redundant yet not fully behaviorally neutral. A zero-
retrieval control confirms that these effects arise from degradation of meaningful
retrieval. A two-support ablation further shows that multi-hop evidence items can interact non-additively: removing both supports harms performance far more than either single removal. Our results suggest that answer-only evaluation misses important evidence effects and that intervention-based utility analysis is a practical complement for RAG evaluation.
Read the full abstract ▾
Computation and Language
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
Yifeng He, Ziye Tang and Hao Chen
Information cocoons on social media limit users' exposure to posts with diverse viewpoints. Modern platforms use stance detection as an important signal in recommendation and ranking pipelines, which can route posts primarily to like-minded audiences and reduce cross-cutting exposure. This restricts the reach of dissenting opinions and hinders constructive discourse. We take the creator's perspective and investigate how content can be revised to reach beyond existing affinity clusters. We present ContentFuzz, a confidence-guided fuzzing framework that rewrites posts while preserving their human-interpreted intent and induces different machine-inferred stance labels. ContentFuzz aims to route posts beyond their original cocoons. Our method guides a large
language model (LLM) to generate meaning-preserving rewrites using confidence feedback from stance detection models. Evaluated on four representative stance detection models across three
datasets in two
languages, ContentFuzz effectively changes machine-classified stance labels, while maintaining semantic integrity with respect to the original content.
Read the full abstract ▾
Computation and Language
Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
Qiyuan Chen, Hongsen Huang, Jiahe Chen et al. (+6 more)
Vision-
language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as opaque "black boxes." To bridge this gap, we propose VL-MDR (
Vision-
Language Multi-Dimensional Reward), a framework that dynamically decomposes evaluation into granular, interpretable dimensions. Instead of outputting a monolithic scalar, VL-MDR employs a visual-aware gating mechanism to identify relevant dimensions and adaptively weight them (e.g.,
Hallucination,
Reasoning) for each specific input. To support this, we curate a
dataset of 321k
vision-
language preference pairs annotated across 21 fine-grained dimensions. Extensive experiments show that VL-MDR consistently outperforms existing open-source reward models on
benchmarks like VL-RewardBench. Furthermore, we show that VL-MDR-constructed preference pairs effectively enable DPO
alignment to mitigate visual
hallucinations and improve reliability, providing a scalable solution for VLM
alignment.
Read the full abstract ▾
All authors Qiyuan Chen, Hongsen Huang, Jiahe Chen, Qian Shao, Jintai Chen, Hongxia Xu, Renjie Hua, Chuan Ren, Jian Wu
Computation and Language · Cross-listed from cs.LG
Residual-Mass Accounting for Partial-KV Decoding
Yasuto Hoshi, Daisuke Miyashita and Jun Deguchi
We study a controlled partial-KV decoding setting in which exact unnormalized softmax contributions are computed for sink/tail anchors and a retrieved
token set, while the remaining prefill
tokens are represented by a residual estimate. We focus on the accounting rule after the query-dependent exact support has been selected, and use exhaustive Top-K only as an oracle selector, not as a deployable
retrieval system. The proposed rule leaves the backbone
language model and the exact-branch KV tensors unchanged. It builds fixed-size summary states $(S,u)$ from learned positive feature maps $\phi$, subtracts retrieved-
token feature contributions to keep the exact and residual sets non-overlapping, and merges the estimated residual numerator and denominator with the exact branch under one normalization. At a 1% exact-support budget, our residual-completion method improves over the selection-only Top-K baseline on RULER and BABILong across frozen 1B and 3B Llama-3.2-Instruct backbones at all reported context lengths. In the 0.5-4% exact-support budget sweeps, this trend largely persists. On LongBench, summarization results are mostly favorable, while multi-document QA is mixed.
Attention-output diagnostics support retrieved-
token subtraction as the partition-consistent accounting rule, while indicating that the main remaining error is imperfect learned-$\phi$ approximation of the unretrieved residual mass.
Read the full abstract ▾
Computation and Language · Cross-listed from eess.SY
Bridging Natural Language and Microgrid Dynamics: A Context-Aware Simulator and Dataset
Tinko Sebastian Bartels, Ruixiang Wu, Xinyu Lu et al. (+5 more)
Addressing the critical need for intelligent, context-aware energy management in renewable systems, we introduce the OpenCEM Simulator and
Dataset: the first open-source digital twin explicitly designed to integrate rich, unstructured contextual information with quantitative renewable energy dynamics. Traditional energy management relies heavily on numerical time series, thereby neglecting the significant predictive power embedded in human-generated context (e.g., event schedules, system logs, user intentions). OpenCEM bridges this gap by offering a unique platform comprising both a meticulously aligned,
language-rich
dataset from a real-world PV-and-battery microgrid installation and a modular simulator capable of natively processing this multi-modal context. The OpenCEM Simulator provides a high-fidelity environment for developing and validating novel control
algorithms and prediction models, particularly those leveraging Large
Language Models. We detail its component-based architecture, hybrid data-driven and physics-based modelling capabilities, and demonstrate its utility through practical examples, including context-aware load
forecasting and the implementation of online optimal battery charging control strategies. By making this platform publicly available, OpenCEM aims to accelerate research into the next generation of intelligent, sustainable, and truly context-aware energy systems.
Read the full abstract ▾
All authors Tinko Sebastian Bartels, Ruixiang Wu, Xinyu Lu, Yikai Lu, Fanzeng Xia, Haoxiang Yang, Yue Chen, Tongxin Li
Computation and Language · Cross-listed from cs.AI
PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection
Siyuan Cheng, Bozhong Tian, YanChao Hao et al. (+1 more)
PRISM-MCTS: Learning from
Reasoning Trajectories with Metacognitive Reflection Siyuan Cheng, Bozhong Tian, Yanchao Hao, Zheng Wei Published: 06 Apr 2026, Last Modified: 06 Apr 2026 ACL 2026 Findings Conference, Area Chairs, Reviewers, Publication Chairs, Authors Revisions BibTeX CC BY 4.0 Keywords: Efficient/Low-Resource Methods for NLP, Generation, Question Answering Abstract: The emergence of
reasoning models, exemplified by OpenAI o1, signifies a transition from intuitive to deliberative cognition, effectively reorienting the scaling laws from pre-training paradigms toward test-time computation. While Monte Carlo Tree Search (MCTS) has shown promise in this domain, existing approaches typically treat each rollout as an isolated trajectory. This lack of information sharing leads to severe inefficiency and substantial computational redundancy, as the search process fails to leverage insights from prior explorations. To address these limitations, we propose PRISM-MCTS, a novel
reasoning framework that draws inspiration from human parallel thinking and reflective processes. PRISM-MCTS integrates a Process Reward Model (PRM) with a dynamic shared
memory, capturing both "Heuristics" and "Fallacies". By reinforcing successful strategies and
pruning error-prone branches, PRISM-MCTS effectively achieves refinement. Furthermore, we develop a data-efficient training strategy for the PRM, achieving high-fidelity evaluation under a few-shot regime. Empirical evaluations across diverse
reasoning benchmarks substantiate the efficacy of PRISM-MCTS. Notably, it halves the trajectory requirements on GPQA while surpassing MCTS-RAG and Search-o1, demonstrating that it scales inference by
reasoning judiciously rather than exhaustively.
Read the full abstract ▾
All authors Siyuan Cheng, Bozhong Tian, YanChao Hao, Zheng Wei
Computation and Language
Multi-Drafter Speculative Decoding with Alignment Feedback
Taehyeon Kim, Hojung Jung and Se-Young Yun
Speculative decoding (SD) accelerates large
language model (LLM) inference by using a smaller model to draft future
tokens, which are then verified by the target LLM. This preserves generation quality by accepting only aligned
tokens. However, individual drafters, often trained for specific tasks or domains, exhibit limited effectiveness across diverse applications. To address this, we introduce MetaSD, a unified framework that integrates multiple drafters into the SD process. MetaSD dynamically allocates computational resources to heterogeneous drafters by leveraging
alignment feedback and framing drafter selection as a multi-armed bandit problem. Extensive experiments show MetaSD consistently outperforms single-drafter approaches.
Read the full abstract ▾
Computation and Language
Confidence Should Be Calibrated More Than One Turn Deep
Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu et al. (+3 more)
Large
Language Models (LLMs) are increasingly applied in high-stakes domains such as finance, healthcare, and education, where reliable multi-turn interactions with users are essential. However, existing work on confidence estimation and calibration, a major approach to building trustworthy LLM systems, largely focuses on single-turn settings and overlooks the risks and potential of multi-turn conversations. In this work, we introduce the task of multi-turn calibration to reframe calibration from a static property into a dynamic challenge central to reliable multi-turn conversation, where calibrating model confidence at each turn conditioned on the conversation history is required. We first reveal the risks of this setting: using Expected Calibration Error at turn T (ECE@T), a new metric that tracks calibration dynamics over turns, we show that user feedback (e.g., persuasion) can degrade multi-turn calibration. To address this, we propose MTCal, which minimises ECE@T via a surrogate calibration target, and further leverage calibrated confidence in ConfChat, a decoding strategy that improves both factuality and consistency of the model response in multi-turn interactions. Extensive experiments demonstrate that MT-Cal achieves outstanding and consistent performance in multi-turn calibration, and ConfChat preserves and even enhances model performance in multi-turn interactions. Our results mark multi-turn calibration as one missing link for scaling LLM calibration toward safe, reliable, and real-world use.
Read the full abstract ▾
All authors Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu, Chao Shen, Ziquan Liu, Ioannis Patras
Computation and Language · Cross-listed from cs.IR
Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA
Xing Tang, Hao Chen, Shiwei Li et al. (+7 more)
Large
language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financial domain. An online financial question-answering system can leverage both LLMs and private APIs to provide timely financial analysis and information. The key is equipping the LLM model with function calling capability tailored to a financial scenario. However, a generic LLM requires customized financial APIs to call and struggles to adapt to the financial domain. Additionally, online user queries are diverse and contain out-of-distribution parameters compared with the required function input parameters, which makes it more difficult for a generic LLM to serve online users. In this paper, we propose a data-driven pipeline to enhance function calling in LLM for our online, deployed financial QA, comprising
dataset construction, data augmentation, and model training. Specifically, we construct a
dataset based on a previous study and update it periodically, incorporating queries and an augmentation method named AugFC. The addition of user query-related samples will exploit our financial toolset in a data-driven manner, and AugFC explores the possible parameter values to enhance the diversity of our updated
dataset. Then, we train an LLM with a two-step method, which enables the use of our financial functions. Extensive experiments on existing offline
datasets, as well as the deployment of an online scenario, illustrate the superiority of our pipeline. The related pipeline has been adopted in the financial QA of YuanBao\footnote{https://yuanbao.tencent.com/chat/}, one of the largest chat platforms in China.
Read the full abstract ▾
All authors Xing Tang, Hao Chen, Shiwei Li, Fuyuan Lyu, Weijie Shi, Lingjie Li, Dugang Liu, Weihong Luo, Xiku Du, Xiuqiang He
Computation and Language
ICR-Drive: Instruction Counterfactual Robustness for End-to-End Language-Driven Autonomous Driving
Kaiser Hamid, Can Cui and Nade Liang
Recent progress in
vision-
language-action (VLA) models has enabled
language-conditioned driving
agents to execute natural-
language navigation commands in closed-loop simulation, yet standard evaluations largely assume instructions are precise and well-formed. In deployment, instructions vary in phrasing and specificity, may omit critical qualifiers, and can occasionally include misleading, authority-framed text, leaving instruction-level robustness under-measured. We introduce ICR-Drive, a diagnostic framework for instruction counterfactual robustness in end-to-end
language-conditioned autonomous driving. ICR-Drive generates controlled instruction variants spanning four perturbation families: Paraphrase, Ambiguity, Noise, and Misleading, where Misleading variants conflict with the
navigation goal and attempt to override intent. We replay identical CARLA routes under matched simulator configurations and seeds to isolate performance changes attributable to instruction
language. Robustness is quantified using standard CARLA Leaderboard metrics and per-family performance degradation relative to the baseline instruction. Experiments on LMDrive and BEVDriver show that minor instruction changes can induce substantial performance drops and distinct failure modes, revealing a reliability gap for deploying
embodied foundation models in safety-critical driving.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
Xuan Xiong, Huan Liu, Li Gu et al. (+4 more)
Chain-of-thought (CoT)
reasoning improves large
language model performance on complex tasks, but often produces excessively long and inefficient
reasoning traces. Existing methods shorten CoTs using length penalties or global
entropy reduction, implicitly assuming that low uncertainty is desirable throughout
reasoning. We show instead that
reasoning efficiency is governed by the trajectory of uncertainty. CoTs with dominant downward
entropy trends are substantially shorter. Motivated by this insight, we propose
Entropy Trend Reward (ETR), a trajectory-aware objective that encourages progressive uncertainty reduction while allowing limited local exploration. We integrate ETR into Group Relative Policy Optimization (GRPO) and evaluate it across multiple
reasoning models and challenging
benchmarks. ETR consistently achieves a superior accuracy-efficiency tradeoff, improving DeepSeek-R1-Distill-7B by 9.9% in accuracy while reducing CoT length by 67% across four
benchmarks. Code is available at https://github.com/Xuan1030/ETR
Read the full abstract ▾
All authors Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao Yu, Yang Wang
Computation and Language
DQA: Diagnostic Question Answering for IT Support
Vishaal Kapoor, Mariam Dundua, Sarthak Ahuja et al. (+6 more)
Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While
retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns. We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting,
retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints. We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7% success rate under a trajectory-level success criterion, compared to 41.3% for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9.
Read the full abstract ▾
All authors Vishaal Kapoor, Mariam Dundua, Sarthak Ahuja, Neda Kordjazi, Evren Yortucboylu, Vaibhavi Padala, Derek Ho, Jennifer Whitted, Rebecca Steinert
Computation and Language
Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
Xiangxu Zhang, Jiamin Wang, Qinlin Zhao et al. (+6 more)
As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing
attention. Nevertheless, it is still unclear why human values matter for LLMs, especially in LLM-based multi-
agent systems, where group-level failures may accumulate from individually misaligned actions. We ask whether misalignment with human values alters the collective behavior of LLM
agents and what changes it induces? In this work, we introduce CIVA, a controlled multi-
agent environment grounded in social science theories, where LLM
agents form a community and autonomously communicate, explore, and compete for resources, enabling systematic manipulation of value prevalence and behavioral analysis. Through comprehensive simulation experiments, we reveal three key findings. (1) We identify several structurally critical values that substantially shape the community's collective dynamics, including those diverging from LLMs' original orientations. Triggered by the misspecification of these values, we (2) detect system failure modes, e.g., catastrophic collapse, at the macro level, and (3) observe emergent behaviors like deception and power-seeking at the micro level. These results offer quantitative evidence that human values are essential for collective outcomes in LLMs and motivate future multi-
agent value
alignment.
Read the full abstract ▾
All authors Xiangxu Zhang, Jiamin Wang, Qinlin Zhao, Hanze Guo, Linzhuo Li, Jing Yao, Xiao Zhou, Xiaoyuan Yi, Xing Xie
Computation and Language
DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects
Jason Lucas, Matt Murtagh, Ali Al-Lawati et al. (+3 more)
Harmful content detectors, particularly disinformation classifiers, are predominantly developed and evaluated on Standard American English (SAE), leaving their robustness to dialectal variation unexplored. We present DIA-HARM, the first
benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE's linguistically grounded transformations, we introduce D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of DIA-HARM comprising 195K samples derived from established disinformation
benchmarks. Our evaluation of 16 detection models reveals systematic vulnerabilities: human-written dialectal content degrades detection by 1.4-3.6% F1, while AI-generated content remains stable. Fine-tuned
transformers substantially outperform zero-shot LLMs (96.6% vs. 78.3% best-case F1), with some models exhibiting catastrophic failures exceeding 33% degradation on mixed content. Cross-dialectal transfer analysis across 2,450 dialect pairs shows that
multilingual models (mDeBERTa: 97.2% average F1) generalize effectively, while monolingual models like RoBERTa and XLM-RoBERTa fail on dialectal inputs. These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-SAE speakers worldwide. We release the DIA-HARM
benchmark, including the D-CUBE corpus (https://github.com/jsl5710/dia-harm), and evaluation tools (https://jsl5710.github.io/dia-harm).
Read the full abstract ▾
All authors Jason Lucas, Matt Murtagh, Ali Al-Lawati, Uchendu Uchendu, Adaku Uchendu, Dongwon Lee
Computation and Language · Cross-listed from cs.LG
LLMs Should Express Uncertainty Explicitly
Junyu Guo, Shangding Gu, Ming Jin et al. (+2 more)
Large
language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is uncertain, can it be trained to signal so within its own response? A central design question is where in the response this signal should be exposed – during
reasoning, while the answer is still being formed, or at the end, once the answer has been produced. We study both. For end-of-
reasoning self-assessment, we train the model to verbalize a confidence score for its response, with the aim of high confidence on correct answers and low confidence on incorrect ones. For during-
reasoning self-assessment, we train the model to emit the marker <uncertain> whenever its current
reasoning state appears unreliable. Across factual
reasoning tasks, both forms sharply reduce overconfident errors while improving answer quality, and both can be used as triggers for
retrieval augmented generation (RAG) to improve the final response. We further analyze their internal mechanisms: end-of-
reasoning verbalized confidence sharpens a confidence-related structure already present in the pretrained model, whereas during-
reasoning <uncertain> emission teaches the model to mark high-risk
reasoning steps, with parameter changes concentrated in the model's late layers.
Read the full abstract ▾
All authors Junyu Guo, Shangding Gu, Ming Jin, Costas Spanos, Javad Lavaei
Computation and Language
Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification
Jinhong Jeong, Junghun Park and Youngjae Yu
Text simplification supports second
language (L2) learning by providing comprehensible input, consistent with the Input Hypothesis. However, constructing personalized parallel corpora is costly, while existing large
language model (LLM)-based readability control methods rely on pre-labeled sentence corpora and primarily target English. We propose Re-RIGHT, a unified reinforcement learning framework for adaptive
multilingual text simplification without parallel corpus supervision. We first show that prompting-based lexical simplification at target proficiency levels (CEFR, JLPT, TOPIK, and HSK) performs poorly at easier levels and for non-English
languages, even with state-of-the-art LLMs such as GPT-5.2 and Gemini 2.5. To address this, we collect 43K vocabulary-level data across four
languages (English, Japanese, Korean, and Chinese) and train a compact 4B policy model using Re-RIGHT, which integrates three reward modules: vocabulary coverage, semantic preservation, and coherence. Compared to the stronger LLM baselines, Re-RIGHT achieves higher lexical coverage at target proficiency levels while maintaining original meaning and fluency.
Read the full abstract ▾
Computation and Language
Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext
Kabir Ahuja, Yuxuan Li and Andrew Kyle Lampinen
Human communication is fundamentally creative, and often makes use of subtext – implied meaning that goes beyond the literal content of the text. Here, we systematically study whether
language models can use subtext in communicative settings, and introduce four new evaluation suites to assess these capabilities. Our evaluation settings range from writing & interpreting allegories to playing multi-
agent and multi-modal games inspired by the rules of board games like Dixit. We find that frontier models generally exhibit a strong bias towards overly literal, explicit communication, and thereby fail to account for nuanced constraints – even the best performing models generate literal clues 60% of times in one of our environments – Visual Allusions. However, we find that some models can sometimes make use of common ground with another party to help them communicate with subtext, achieving 30%-50% reduction in overly literal clues; but they struggle at inferring presence of a common ground when not explicitly stated. For allegory understanding, we find paratextual and persona conditions to significantly shift the interpretation of subtext. Overall, our work provides quantifiable measures for an inherently complex and subjective phenomenon like subtext and reveals many weaknesses and idiosyncrasies of current LLMs. We hope this research to inspire future work towards socially grounded creative communication and
reasoning.
Read the full abstract ▾