Skip to content
conftrace_

AACL 2026

736 papers

Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification

Sunisth Kumar, Xanh Ho, Tim Schopf, Andre Greiner-Petter, Florian Boudin

Polar: A Benchmark for Evaluating Political Bias in LLMs

Sangho Kim, Heejin Kim, Hyunggeun Jeon, Yoonhee Park, Jaejin Lee

Beyond EOS: Revealing the Internal Monologue of Language Models

Aishwarya Maheswaran, Maunendra Sankar Desarkar

IMFD: End-to-end Multi-Face Forgery Detection through Instruction-based Large Vision-Language Models

Dasom Choi, Sangjun Moon, Hyeongchan Im, Jaeeon Park, Jingun Kwon

TripPattern: A Pattern-based Text Watermarking Method for Large Language Models

Sangjun Moon, Dasom Choi, Jingun Kwon, Hidetaka Kamigaito, Taro Watanabe

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation

Jiayi Li, Shijie Tang, Gün Kaynar, Shiyi Du, Carl Kingsford

One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction

Hongliang Li, Lu Wang, Yong Xu, Hanyang Chen, Zhitao Hou

CASCADE: Cognitive Assessment via Sentence Context and Distortion Extraction

Archit Narumanchi, Azamat Rashidov, Jong C. Park

Structured but Silent: Probing Capability Requirements in LLM Hidden States

Kyojun Choo, Minsoo Song, Yunju Kang, Chanjun Park

OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement

Sihyeon Lee, Jihun Song, Chanwoo Kim, Jiwoo Kum, Chanjun Park

When and How to use In-context Learning for modern LVLMs? An Extensive Investigation

Pengxiang Li, Yu Zhao, Jiaxin Yu, Liang Xie, Erwei Yin

When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study

Mohit Singh Chauhan, Vipin Gyanchandani, Dylan Bouchard

Copy Less, Ground More: Selective and Confidence-Aware Decoding for Grounded Legal Generation

Tan-Minh Nguyen, Dinh-Truong Do, Hiep K. V. Nguyen, Le-Minh Nguyen

InLegalLaySum: A Novel Benchmark for Lay Summarization of Indian Legal Documents

Trishita Saha, Debtanu Datta, Shubham Tiwari, Mohit Kaushal, Priyank Rathore

BlockBench: Contamination-Controlled Evaluation of Large Language Models for Code Analysis

Paul Osemudiame Oamen, Courage Ochuko Mene, Abraham Ugbedeojo Daniel, Ananya Mukherjee, Pius Onobhayedo

AI-Sustainability Discourse Across Social Media: Sentiment, Topics, and Engagement on LinkedIn, X, and Bluesky

Kholoud Khalil Aldous, Md. Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, Kais Attia

Corrective Retrieval Augmented Generation

Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, Zhen-Hua Ling

How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices

Liulei Zhang, Dejing Zhou, Chuyue Huang, Guanhua Chen, Yutong Yao

CULTURETALK-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages

Muhammad Dehan Al Kautsar, Salsabila Zahirah Pranida, Bilal Elbouardi, Fajri Koto

Modeling Discourse Profiles in Climate Misinformation Discourse

Ge Gao, Zhengyang Shan, Bryan A. Plummer, Margrit Betke, Derry Tanti Wijaya

When more supervision hurts: reward design for structured biomedical reasoning in 4B models

Batuhan Nursal, Christophe Ye, Xinyu Guo, XIN HE, Cassie S. Mitchell

DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data

Xin Li, Jin Li, Shoujin Wang, Kun Yu, Fang Chen

An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages

Yinhan Lu, Gaganpreet Jhajj, Chen Zhang, Anietie Andy, David Ifeoluwa Adelani

FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models

Zahraa Al Sahili, Maimuna Nowaz, Maryam Fetanat, Ioannis Patras, Matthew Purver

Activation Residual Hessian Quantization for Low-Bit Large Language Model Inference

Yifeng Wang, Zhun Sun, Hakaze Cho, Linlin Wang, Keisuke Sakaguchi

Pingala: Prosody-Aware Decoding for Sanskrit Poetry Generation

Manoj Balaji Jagadeeshan, Atul Singh, Nallani Chakravartula Sahith, Amrith Krishna, Pawan Goyal

The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue

Sherzod Hakimov, Mattia D’Agostini, Ivan Samodelkin, David Schlangen

Selective Reflection for Context-Sensitive Emotion Recognition in Conversation

Xinyu Wang, Weijie Feng, Hongchuang Wang, Zhiyong Cheng

Quantifying Uncertainty Through Coverage in Latent Semantic Space

Gabriele Carrino, Brown Ebouky, Katja Hose, Mattia Rigotti

GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos

Minghan Li, Tongna Chen, Tianrui Lv, Yishuai Zhang, Suchao An

NüshuVoice: Reviving the Voice of Endangered Nüshu with Pitch-Aware Text-to-Speech

Hongkun Yang, YI Xinhui, Zhao Xiyan, Yibo Meng, Lionel Z. Wang

SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation

Yixi Zhou, Fan Zhang, Zhiqiao Guo, Yu Chen, Haipeng Zhang

ProgMem: Programmatic Belief-State Memory for Long-Horizon Conversational Agents

Pengchao Zheng, Xinan Wang, Ziyi Wei, Haoran Liu, Lei Wei

Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design

Omar Sharif, Eftekhar Hossain, Nikhil Singh, Patrick Ng

HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers

Issa Sugiura, Shuhei Kurita, Yusuke Oda, Naoaki Okazaki

Markhor: A framework for Adapting LLMs to Urdu via Alignment-Free Tokenizer Replacement

Muhammad Zain Ali, Yuxia Wang, Muhammad Arslan Manzoor, Tony C Smith, Bernhard Pfahringer

NEXUS: Structured Runtime Safety for Tool-Using LLM Agent

Elias Hossain, Md Mehedi Hasan Nipu, Tasfia Nuzhat Ornee, Rajib Rana, Niloofar Yousefi

DunbaaBERT: From Sacrifice to Semantics

Iffat Maab, Waleed Jamil, Raphael Schmitt

TokenMapper: A Step Toward Interoperable Speech Token Translation

Tal Kozakov, Tal Rosenwein, Eliya Nachmani

Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models

Xiutian Zhao, İsmail Rasim Ülgen, Philipp Koehn, Björn Schuller, Berrak Sisman

LecTrans: A Multimodal Translation Benchmark for Academic Lectures

Frederikus Hudi, Nina Nanakorn, Justin Vasselli, Yusuke Sakai, Hidetaka Kamigaito

AGOPNs: Null-Space Activation Steering for Jailbreak Defense via Average Gradient Outer Product Concept Extraction

Minh-Nguyen Bui, Binh-Phuong Phan, Thanh-Khang Doan, Bao Huynh-Gia, Phung-Anh Nguyen

FACTA: Structured Fact Alignment for Multi-Hop Retrieval-Augmented Generation

Jiahao Li, Yongxiu Xu, Xumeng Zhang, Hongbo Xu, Minghao Tang