Papers
Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents
Ankan Mullick, Sombit Bose, Rounak Saha et al.
Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning
Junjie Xing, Yeye He, Mengyu Zhou et al.
Towards Robust Mathematical Reasoning
Thang Luong, Dawsen Hwang, Hoang H Nguyen et al.
D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering
Guangze Gao, Zixuan Li, Chunfeng Yuan et al.
Evaluating Large Language Models for Detecting Antisemitism
Jay Patel, Hrudayangam Mehta, Jeremy Blackburn
Current Semantic-change Quantification Methods Struggle with Discovery in the Wild
Khonzoda Umarova, Lillian Lee, Laerdon Kim
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations
Linyang He, Qiaolin Wang, Xilin Jiang et al.
Retracing the Past: LLMs Emit Training Data When They Get Lost
Myeongseob Ko, Nikhil Reddy Billa, Adam Nguyen et al.
Not Your Typical Government Tipline: LLM-Assisted Routing of Environmental Protection Agency Citizen Tips
Sharanya Majumder, Zehua Li, Derek Ouyang et al.
CourtReasoner: Can LLM Agents Reason Like Judges?
Sophia Simeng Han, Yoshiki Takashima, Shannon Zejiang Shen et al.
SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
Yao Dou, Michel Galley, Baolin Peng et al.
Quantifying Logical Consistency in Transformers via Query-Key Alignment
Eduard Tulchinskii, Laida Kushnareva, Anastasia Voznyuk et al.
Certified Mitigation of Worst-Case LLM Copyright Infringement
Jingyu Zhang, Jiacan Yu, Marc Marone et al.
so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs
Sriharsh Bhyravajjula, Melanie Walsh, Anna Preus et al.
Statistical and Neural Methods for Hawaiian Orthography Modernization
Jaden Kapali, Keaton Williamson, Winston Wu
A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs
Shaona Ghosh, Amrita Bhattacharjee, Yftah Ziser et al.
BRSpeech-DF: A Deep Fake Synthetic Speech Dataset for Portuguese Zero-Shot TTS
Alexandre Costa Ferro Filho, Rafaello Virgilli, Lucas Alcantara Souza et al.
Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems
Adam Zahradník, Marek Suppa
Retrieving Support to Rank Answers in Open-Domain Question Answering
Zeyu Zhang, Alessandro Moschitti, Thuy Vu
TLUE: A Tibetan Language Understanding Evaluation Benchmark
Fan Gao, Cheng Huang, Yutong Liu et al.
Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space?
Nandan Kumar Jha, Brandon Reagen
Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models
Tomohiro Sawada, Kartik Goyal
Translating Domain-Specific Terminology in Typologically-Diverse Languages: A Study in Tax and Financial Education
Arturo Oncevay, Elena Kochkina, Keshav Ramani et al.
Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Cross-Lingual Transfer in Sense-Aware Tasks
Roksana Goworek, Haim Dubossarsky
FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks
Tanawan Premsri, Parisa Kordjamshidi