AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ACL 2026

Poller: Are LLMs Suitable for Evaluating Poetry Understanding Task?

Shanshan Wang, Derek F. Wong, Jingming Yao, Lidia S. Chao

Traditional automatic evaluation methods have been shown to be unsuitable for modern Chinese poetry because of the distinct nature of this literary genre. Human evaluation remains reliable, but is expensive and not applicable to large-scale data. In this paper, we propose Poller (Poetry LLM Evaluator), a novel method leveraging Large Language Models (LLMs) to evaluate the poetry understanding task. Specifically, our method requires LLMs to play the role of a poem’s author with detailed information, thereby emulating human evaluation and judgment by adopting the poet’s perspective. We conducted comprehensive experiments on multiple LLMs, evaluating the interpretations of poems across eight specialized dimensions. Experimental results demonstrate that our method effectively reduces the evaluation error between LLMs and humans. Especially for specific dimension evaluation, Poller-based LLMs achieve a 94.55% and 89.53% error reduction for rhetorical techniques and defamiliarization, respectively, compared to baseline methods. These performances are unattainable by conventional LLM evaluation methods. Experimental results from multiple LLMs across various dimensions validate the efficacy of our method. This work bridges the gap between automated efficiency and human expertise, establishing a foundation for automated evaluation in poetry-related tasks.

ACL 2026

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models

Wenlong Shi, Jianxun Lian, Mingqi Wu, Haiming Qin, Mingyang Zhou, Xing Xie, Naipeng Chao, Hao Liao

Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research predominantly focuses on character-level settings and relies on static evaluation formats, failing to capture the complexity of everyday social interactions. In this work, we present PersonaArena, a dynamic simulation framework for evaluating and improving persona-level role-playing in LLMs. PersonaArena leverages a large, filtered corpus of user-generated social content to construct a nuanced persona bank, and elicits multi-turn, context-rich interactions within simulated social environments. Our framework features a multi-agent debating judge for holistic and unbiased assessment. Through extensive experiments, we demonstrate that PersonaArena enables rigorous evaluation and enhancement of LLMs’ role-playing capabilities, advancing the development of more authentic and socially adept AI agents. Our codes and long appendix are available at https://anonymous.4open.science/r/PersonaArena-B323/.

ACL 2026

ToolGate: Contract-Grounded and Verified Tool Execution for LLMs

Yanming Liu, Xinyue Peng, Jiannan Cao, Xinyi Wang, Songhang Deng, Jintao Chen, Jianwei Yin, Xuhong Zhang

Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natural language reasoning to determine when tools can be invoked and whether their results should be committed, lacking formal guarantees for logical safety and verifiability. We present ToolGate, a forward execution framework that provides logical safety guarantees and verifiable state evolution for LLM tool calling. ToolGate maintains an explicit symbolic state space as a typed key-value mapping representing trusted world information throughout the reasoning process. Each tool is formalized as a Hoare-style contract consisting of a precondition and a postcondition, where the precondition gates tool invocation by checking whether the current state satisfies the required conditions, and the postcondition determines whether the tool’s result can be committed to update the state through runtime verification. Our approach guarantees that the symbolic state evolves only through verified tool executions, preventing invalid or hallucinated results from corrupting the world representation. Experimental validation demonstrates that ToolGate significantly improves the reliability and verifiability of tool-augmented LLM systems while maintaining competitive performance on complex multi-step reasoning tasks. This work establishes a foundation for building more trustworthy and debuggable AI systems that integrate language models with external tools.

ACL 2026

Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky

Ashutosh Hathidara, Julien Yu, Sebastian Schreiber

Large language models (LLMs) are increasingly tasked with invoking enterprise APIs, yet they routinely falter when near-duplicate tools vie for the same user intent or when required arguments are left underspecified. We introduce DiaFORGE (Dialogue Framework for Organic Response Generation Evaluation), a disambiguation-centric, three-stage pipeline that (i) synthesizes persona-driven, multi-turn dialogues in which the assistant must distinguish among highly similar tools, (ii) performs supervised fine-tuning of open-source models with reasoning traces across 3B - 70B parameters, and (iii) evaluates real-world readiness via a dynamic suite that redeploys each model in a live agentic loop and reports end-to-end goal completion alongside conventional static metrics. On our dynamic benchmark DiaBENCH, models trained with DiaFORGE raise tool-invocation success by 27 pp over GPT-4o and by 49 pp over Claude-3.5-Sonnet, both under optimized prompting. To spur further research, we release an open corpus of 5000 production-grade enterprise API specifications paired with rigorously validated, disambiguation-focused dialogues, offering a practical blueprint for building reliable, enterprise-ready tool-calling agents.

ACL 2026

StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation

Qingyu Meng, Min Chen, Dingming Liu, Yifan Mo, Yue Su, Xin Sun, Koen Hindriks, Jiahuan Pei

Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in motivational interviewing (MI). We introduce StoryMI, a multi-LLM agent framework for controllable MI dialogue generation, where questionnaire-based client profiles are expanded into situational stories that provide narrative context for the dialogue. Therapist and client agents generate MI-coded utterances guided by MI codes selected by the interaction agent, while an interaction agent dynamically coordinates exchanges to control MI strategies during a multi-turn conversation. We propose a two-level evaluation protocol: lexical metrics and MI-specific measures of macro-level counseling strategies, alongside LLM-as-judge and human expert assessments. We construct a dataset of 6K simulated MI dialogues grounded in 1K questionnaire-story pairs, covering 12 MI codes and 13 symptom domains, and benchmark six open- and closed-source LLMs. Our results show that situational grounding and macro-level control can improve MI adherence and clinical plausibility, demonstrating the effectiveness of a structured multi-agent workflow for psychotherapy dialogue generation. We provide code and data for reproducibility.

ACL 2026

MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting

Kangda Wei, Ruihong Huang

Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, GRPO training is computationally intensive and usually takes a long time, which consumes substantial computational resources and creates barriers for academic researchers and smaller organizations with limited GPU budgets. In this paper, we propose MMR-GRPO to accelerate GRPO training and reduce the overall training time required to reach peak performance, and the approach adopts Maximal Marginal Relevanceto reweigh rewards of multiple rollouts by balancing rollout quality with diversity to reduce rollout redundancy. The rationale is that redundant or similar completions, if repeatedly used to train a model, will create an “exploitation trap” and slow down model convergence in GRPO style reinforcement learning. Extensive evaluations across three model sizes (1.5B, 7B, 8B), three GRPO variants, and five mathematical reasoning benchmarks show that MMR-GRPO achieves comparable peak performance while requiring on average 47.9% fewer training steps and 70.2% less wall-clock time. These gains are consistent across models, methods, and benchmarks. Our code is released at: https://github.com/WeiKangda/MMR-GRPO.

ACL 2026

EduMARS: Can Vision-Language Models Grade Like Teachers? Benchmarking Multimodal, Rubric-Based Assessment on Chinese K-12 Answers

Xuan Zhao, Jiashun Chen, Wanting Xu, Huiyuan Yan, Chaowei Fang, Xing Wei

Automated grading of student work is a critical application of AI in education. However, existing benchmarks fall short in evaluating models on realistic, cognitively demanding tasks. Most rely on synthetic, well-structured text inputs, overlooking the multimodal, error-prone, and often handwritten nature of real student responses, especially in K-12 settings. We introduce EduMARS, a multimodal benchmark designed for rubric-aligned evaluation of real Chinese K-12 student answers. The dataset contains over 4,500 authentic responses from high-stakes exams across eight subjects, featuring noisy handwriting,mixed-layout diagrams,mathematical expressions, and narrative reasoning. Each response is meticulously annotated by expert teachers using step-wise scoring rubrics, error classifications, and key-point mappings, providing fine-grained supervision aligned with real-world pedagogical practices. We evaluated existing SOTA MLLMs across the dimensions of final score and the reasoning process of grading, reveals a significant gap between existing SOTA MLLMs and human-level performance. To bridge this performance gap, we propose the Retrieval-Augmented Adaptive-Rubric Grading (RARG), enabling models to emulate expert grading logic by dynamically synthesizing case-specific evaluation schemas. RARG effectively enhances the performance and interpretability of various MLLMs on EduMARS, surpassing in-context learning and chain-of-thought.

ACL 2026

NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in African Low-Resource Languages

Mamadou K. Keita, Christopher Homan, Huy Le

We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language’s grammar and explicitly penalizes the model when it assigns high probability to these linguistically invalid outputs. NSL-MT delivers improvements across all baselines we tested, including 3-12% BLEU gains for well-performing models and 56-89% gains for models lacking decent initial support. Furthermore, NSL-MT provides a 5x data efficiency multiplier: training with 1,000 examples matches or exceeds normal training with 5,000 examples. NSL-MT thus provides a data-efficient alternative training method for settings where parallel data is limited.

ACL 2026

Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration

Ryan Soh-Eun Shim, Kwanghee Choi, Kalvin Chang, Ming-Hao Hsu, Florian Eichin, Zhizheng Wu, Alane Suhr, Michael A. Hedderich, David Harwath, David R. Mortensen, Barbara Plank

Multilingual speech foundation models such as Whisper are trained on web-scale data, where data for each language consists of a myriad of regional varieties. However, different regional varieties often employ different scripts to write the same language, rendering speech recognition output also subject to non-determinism in the output script. To mitigate this problem, we show that script is linearly encoded in the activation space of multilingual speech models, and that modifying activations at inference time enables direct control over output script. We find the addition of such script vectors to activations at test time can induce script change even in unconventional language-script pairings (e.g. Italian in Cyrillic and Japanese in Latin script). We apply this approach to inducing post-hoc control over the script of speech recognition output, where we observe competitive performance across all model sizes of Whisper.

ACL 2026

Conflicts Make Large Reasoning Models Vulnerable to Attacks

Honghao Liu, Chengjin Xu, Xuhui Jiang, Cehao Yang, Shengming Yin, Zhengwu Ma, Lionel Ni, Jian Guo

Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts: internal conflicts that pit alignment values against each other and dilemmas, which impose mutually contradictory choices, including sacrificial, duress, agent-centered, and social forms. Using over 1,300 prompts across five benchmarks, we evaluate three representative LRMs - Llama-3.1-Nemotron-8B, QwQ-32B, and DeepSeek R1 - and find that conflicts significantly increase attack success rates, even under single-round non-narrative queries without sophisticated auto-attack techniques. Our findings reveal through layerwise and neuron-level analyses that safety-related and functional representations shift and overlap under conflict, interfering with safety-aligned behavior. This study highlights the need for deeper alignment strategies to ensure the robustness and trustworthiness of next-generation reasoning models. Our code is available at https://github.com/DataArcTech/ConflictHarm. Warning: This paper contains inappropriate, offensive and harmful content.

ACL 2026

TT-SI: Self-Improving LLM Agents with Test-Time Training

Emre Can Acikgoz, Cheng Qian, Heng Ji, Dilek Hakkani-Tur, Gokhan Tur

One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize to novel tasks after post-training. In practice, gathering large sets of data is inefficient, and training on them is prohibitively expensive; worse, there is no guarantee that the resulting model will handle complex scenarios or generalize better. Moreover, existing techniques rarely assess whether a training sample provides novel information, resulting in unnecessary costs. In this work, we explore a new Test-Time Self-Improvement (TT-SI) algorithm to create more effective and generalizable agentic LMs on-the-fly. TT-SI can be summarized in three steps: (i) first it identifies the samples that model struggles with (self-awareness), (ii) then generates similar examples from detected uncertain samples (self-data augmentation), and (iii) uses these newly generated samples at test-time training (self-improvement). We further explore Test-Time Distillation (TT-D), which leverages a stronger supervisor for targeted data generation. Empirical evaluations across different agent benchmarks demonstrate that TT-SI improves the performance with +5.48% absolute accuracy gain on average across all benchmarks and surpasses other standard learning methods more efficiently. Our findings highlight the promise of TT-SI, demonstrating the potential of self-improvement algorithms at test-time as a new paradigm for building more capable agents toward self-evolution.

ACL 2026

Empowering Reliable Visual-Centric Instruction Following in MLLMs

Weilei He, Feng Ju, Zhiyuan Fan, Rui Min, Minhao Cheng

Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model outputs adhere to user-specified intentions. Nevertheless, existing benchmarks for evaluating MLLMs’ instruction-following capability primarily focus on verbal instructions in the textual modality. These limitations hinder a thorough analysis of instruction-following capabilities, as they overlook the implicit constraints embedded in the semantically rich visual modality. To address this gap, we introduce VC-IFEval, a new benchmark accompanied by a systematically constructed dataset that evaluates MLLMs’ instruction-following ability under multimodal settings. Our benchmark systematically incorporates vision-dependent constraints into instruction design, enabling a more rigorous and fine-grained assessment of how well MLLMs align their outputs with both visual input and textual instructions. Furthermore, by fine-tuning MLLMs on our dataset, we achieve substantial gains in visual instruction-following accuracy and adherence. Through extensive evaluation across representative MLLMs, we provide new insights into the strengths and limitations of current models.

ACL 2026

CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction

Jun Gao, Yun Peng, Qian Qiao, Changhai Zhou, Yuhua Zhou, Shiyang Zhang, Shichao Weng, Zhenchang Xing, Xiaoxue Ren

Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmarks primarily evaluate final output correctness under a single canonical implementation, leaving two critical aspects underexplored: (1) whether LLMs predictions are consistent to functionally equivalent implementations, and (2) whether LLMs can accurately reason about intermediate execution states. We introduce CoRE, a Code Reasoning benchmark that evaluates code reasoning through implementation invariance and process transparency. Extensive evaluations on eight frontier LLMs reveal two fundamental limitations. First, models exhibit a substantial robustness gap, with performance varying significantly across equivalent implementations. Second, we observe superficial execution, where models arrive at correct final outputs without correctly reasoning about intermediate execution states. Together, these findings demonstrate that output-only evaluations are insufficient for assessing code reasoning and position CoRE as a necessary benchmark for evaluating robust and faithful code reasoning.

ACL 2026

The Mark Fades: Adaptive Evolutionary Paraphrase-based Attack against LLM Watermarks

Yusheng Zhao, Jian Zhao, Tianle Zhang, Feng Wei, Xuelong Li

While LLM watermarking is essential for machine- generated content identification, existing paraphrase-based attacks struggle to balance watermark removal efficacy with text quality. We propose TSAPA, a training-free evolutionary framework that models watermark removal as a constrained multi-objective optimization problem. By leveraging genetic algorithms to navigate the Pareto front, TSAPA utilizes a Pseudo-Log-Likelihood (PLL)-guided mutation to precisely target and modify watermark-carrying tokens. Experiments on Qwen3 series (1.7B/8B/32B) across multiple watermark schemes show that TSAPA achieves over 90% attack success rate (ASR) while maintaining high text semantic fidelity, significantly outperforming baselines methods. This work exposes critical vulnerabilities in current watermarks and provides a new perspective for robust evaluation.

ACL 2026

PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving

Yuxuan Dong, Xinyu Zhang, Lingling Zhang, Han Lai, Pengyu Li, Bifan Wei, Yaqiang Wu, Jun Liu

Despite the remarkable progress of Large Language Models (LLMs) in abstract reasoning tasks, they continue to struggle with physics problem solving due to difficulties in decoding implicit constraints and maintaining physical consistency. To address these challenges, Process Reward Models (PRMs) have emerged as a promising approach to verify intermediate reasoning steps. Existing PRMs attempt to mitigate reasoning errors but typically rely on scalar scoring, which lacks the explanatory power necessary to diagnose complex physical misconceptions. In this work, we introduce PhysPRM, a Generative PRM that treats evaluation as a generative task to produce fine-grained diagnoses comprising critiques, final judgments, and specific error types. To facilitate this, we develop an automated data synthesis pipeline to construct PhysPRM30K, a comprehensive training dataset, and PhysProcessBench, a rigorously human-verified benchmark. By employing a two-stage training paradigm that integrates Supervised Fine-Tuning with Group Relative Policy Optimization, PhysPRM significantly enhances the physics reasoning capabilities of various LLMs. Extensive experiments demonstrate that PhysPRM improves performance across seven benchmarks in both Best-of-N and critique refinement strategies.

ACL 2026

Distribution Shift Alignment Helps LLMs Simulate Survey Response Distributions

Ji Huang, Mengfei Li, Shuai Shao

Large language models (LLMs) offer a promising way to simulate human survey responses, potentially reducing the cost of large-scale data collection. However, existing zero-shot methods suffer from prompt sensitivity and low accuracy, while conventional fine-tuning approaches mostly fit the training set distributions and struggle to produce results more accurate than the training set itself, which deviates from the original goal of using LLMs to simulate survey responses. Building on this observation, we introduce Distribution Shift Alignment (DSA), a two-stage fine-tuning method that aligns both the output distributions and the distribution shifts across different backgrounds. By learning how these distributions change rather than fitting training data, DSA can provide results substantially closer to the true distribution than the training data. Empirically, DSA consistently outperforms other methods on five public survey datasets. We further conduct a comprehensive comparison covering accuracy, robustness, and data savings. DSA reduces the required real data by 53.48-69.12%, demonstrating its effectiveness and efficiency in survey simulation.

ACL 2026

AlphaQuanter: An End-to-End Tool-Augmented Agentic Reinforcement Learning Framework for Stock Trading

Zheye Deng, Weixiang Yan, Changlong Yu, Jiashu Wang

While Large Language Model (LLM) agents show promise in automated trading, they still face critical limitations. Prominent multi-agent frameworks often suffer from inefficiency, produce inconsistent signals, and lack the end-to-end optimization required to learn a coherent strategy from market feedback. To address this, we introduce AlphaQuanter, a single-agent framework that uses reinforcement learning (RL) to learn a dynamic policy over a transparent, tool-augmented decision workflow, which empowers a single agent to autonomously orchestrate tools and proactively acquire information on demand, establishing a transparent reasoning process. Extensive experiments demonstrate that AlphaQuanter achieves state-of-the-art performance on key financial metrics. Besides, human evaluation shows the learned reasoning patterns reveal more faithful and coherent tool-usage behaviors, providing steps toward verifiable LLM-driven trading. Our code and data can be found at https://github.com/horizon-llm/AlphaQuanter.

ACL 2026

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

Xuhao Hu, Wang Peng, Xiaoya Lu, Dongrui Liu, Xuanjing Huang, Jing Shao

Previous research has shown that LLMs finetuned on incorrect completions within narrow domains (\textit{e.g.}, insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called \textit{emergent misalignment}. In this work, we investigate whether this phenomenon can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios (\textit{e.g.}, lying under pressure and deceptive behavior). To explore this, we finetune open-sourced LLMs on misaligned completions across diverse domains. Experimental results demonstrate that LLMs show broadly misaligned behavior in dishonesty. Additionally, we further explore this phenomenon in a downstream combined finetuning setting, and find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%. Furthermore, we consider a more practical human-AI interaction environment where we simulate both benign and biased users to interact with the assistant LLM. Furthermore, we simulate both benign and biased users to interact with the assistant LLM, producing 20k trajectories for self-training in a more practical human-AI interaction environment. Notably, we find that the assistant model can be misaligned unintentionally to exacerbate its dishonesty with only 10% biased user population. In summary, we extend the study of \textit{emergent misalignment} to the domain of dishonesty under high-stakes scenarios, and highlight that this risk arises not only through direct finetuning, but also in downstream mixture tasks and human-AI interactions.

ACL 2026

How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects

Leonardo Bertolazzi, Sandro Pezzelle, Raffaella Bernardi

Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning problem influences judgments regarding its logical validity. While this phenomenon in humans is best explained by the dual-process theory of reasoning, the mechanisms behind content effects in LLMs remain unclear. In this work, we address this issue by investigating how LLMs encode the concepts of validity and plausibility within their internal representations. We show that both concepts are linearly represented and strongly aligned in representational geometry, leading models to conflate plausibility with validity. Using steering vectors, we demonstrate that plausibility vectors can causally bias validity judgements, and vice versa, and that the degree of alignment between these two concepts predicts the magnitude of behavioral content effects across models. Finally, we construct debiasing vectors that disentangle these concepts, reducing content effects and improving reasoning accuracy. Our findings advance understanding of how abstract logical concepts are represented in LLMs and highlight representational interventions as a path toward more logical systems.

ACL 2026

FACTS: Table Summarization via Offline Template Generation with Agentic Workflows

Ye Yuan, Mohammad Amin Shabani, Siqi Liu

Query-focused table summarization requires generating natural language summaries of tabular data conditioned on a user query, enabling users to access insights beyond fact retrieval. Existing approaches face key limitations: table-to-text models require costly fine-tuning and struggle with complex reasoning, prompt-based LLM methods suffer from token-limit and efficiency issues while exposing sensitive data, and prior agentic pipelines often rely on decomposition, planning, or manual templates that lack robustness and scalability. To mitigate these issues, we introduce an agentic workflow, FACTS, a Fast, Accurate, and Privacy-Compliant Table Summarization approach via Offline Template Generation. FACTS produces offline templates, consisting of SQL queries and Jinja2 templates, which can be rendered into natural language summaries and are reusable across multiple tables sharing the same schema. It enables fast summarization through reusable offline templates, accurate outputs with executable SQL queries, and privacy compliance by sending only table schemas to LLMs. Evaluations on widely-used benchmarks show that FACTS consistently outperforms baseline methods, establishing it as a practical solution for real-world query-focused table summarization. Our code is available at https://github.com/BorealisAI/FACTS.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.