Papers
PExA: Parallel Exploration Agent for Complex Text-to-SQL
Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang et al.
Defense Against Knowledge Poisoning Attack on GraphRAG
Havva Alizadeh Noughabi, Fattane Zarrinkalam, Ali Dehghantanha
On the Rejection Criterion for Proxy-based Test-time Alignment
Ayoub Hammal, Pierre Zweigenbaum, Caio Corro
Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
Cheng Wang, Qin Liu, Wenxuan Zhou et al.
The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
Xi Fang, Weijie Xu, Yuchong Zhang et al.
Dark & Stormy: Modeling Humor in Sentences from the Bulwer-Lytton Fiction Contest
Venkata S Govindarajan, Laura Biester
Pref-CTRL: Preference Driven LLM Alignment using Representation Editing
Imranul Ashrafi, Inigo Jauregi Unanue, Massimo Piccardi
Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning
Trapoom Ukarapol, Pakhapoom Sarapat, Nut Chukamphaeng
GOLEMcoref: A Multilingual Coreference Dataset of Fiction
Andreas Van Cranenburgh, Xiaoyan Yang, Alvanita et al.
UERLens: Understanding Event Relations in Large Language Models
Yong Guan, Zhiyuan Li, Shaoru Guo
DIXITWORLD: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
Yunxiang MO, Tianshi Zheng, Qing Zong et al.
Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
Alberto Testoni, Iacer Calixto
Selective Span-Level Unlearning for Large Language Models
Chaewon Yoon, Dongjun Kim, Hyun-Je Song
When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation
Rhea Kapur, Robert D. Hawkins, Elisa Kreiss
Reliable Evaluation Protocol for Low-Precision Retrieval
Kisu Yang, Yoonna Jang, Hwanseok Jang et al.
From Narrow Unlearning to Emergent Misalignment in LLMs
Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna et al.
Luring as a Proxy: Evaluating Corpus Transferability for Cybergrooming Detection
Shiying Fan, Mareike Bassenge, Martin Steinebach
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
Jeffrey George Wang, Jason Wang, Marvin Li et al.
Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages
Danlu Chen, Ka Sing He, Jiahe Tian et al.
Rethinking Data Mixing from the Perspective of Large Language Models
Yuanjian Xu, Tianze Sun, Changwei Xu et al.
Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks
Atsuki Yamaguchi, Maggie Mi, Nikolaos Aletras
Privacy-preserving Prosody Representation Learning
Kevin Everson, Mari Ostendorf
Prefix Parsing is Just Parsing
Clemente Pasti, Andreas Opedal, Timothy J. O’Donnell et al.
MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation
Yi Lin, Yihao Ding, Yonghui Wu et al.