Papers
Confidence as a Tie-Breaker: Reassessing Multilingual Hedging Bias in LLM-as-a-Judge Evaluation
Rajashik Datta, Sanjan Baitalik
Garden Path Recovery in Causal and Masked Language Models
Sanjan Baitalik, Rajashik Datta
Constructing a Japanese Rap Lyric Generation Model with GRPO
Hayato Ogawa, Daisuke Kawahara
Presentation Slide Translation and Layout Error Correction by LLMs
Futo Kajita, Nobuyori Nishimura, Takehito Utsuro et al.
LLM-based Literal Example Generation for Japanese Multiword Expressions
Mio Ohashi, Hajime Kiyama, Zhidong Ling et al.
The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces
Angelina Tsai, Shreya Subramanian, Catherine Liu et al.
BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction
Tanvir Ahmed Sijan, S. M. Golam Rifat, Pankaj Partha et al.
NEAT-IR: Neural Explainable Analysis Tool for Information Retrieval
Lev Sukherman, Artem Frenk, Nina Klimenkova et al.
Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models
Jacek Duszenko, Przemyslaw Kazienko, Jan Kocon
Phase Transitions in Affective Meaning Divergence: The Hidden Drift Before the Break
Napassorn Litchiowong
TokLens: A Multilingual Lens on Tokenizer Quality for LLMs
Guan-Ming Chiu
Probing Functional Correctness in Diffusion Language Models
Guan-Ming Chiu, Jeng-Yue Liu
Think Less, Code Better: Probing When Chain-of-Thought Hurts and How to Route Around It
Rajarshi Ghoshal, Debadri Basak, Salma Emad Mahmoud Abdelhalim et al.
Peek2: Regex-free Byte-level Byte-Pair Encoding Pretokenizer for LLM Inference on Edge Devices
Liu Zai, Iraklis A. Klampanos
Thesis Proposal: LLMs post-training for multilingual medical tasks. Instruction-Tuning, Continual-Pretraining or Reasoning?
Pietro Ferrazzi, Alberto Lavelli, Bernardo Magnini
Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
Shiyan Liu, Qifeng Xia, Qiyun Xia et al.
Why Large Language Models can Secretly Outperform Embedding Similarity in Information Retrieval
Matei Benescu, Ivo Pascal de Jong