Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation Paper โข 2510.02306 โข Published about 1 month ago โข 3
WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers Paper โข 2509.10452 โข Published Sep 12 โข 1
Lost in Embeddings: Information Loss in Vision-Language Models Paper โข 2509.11986 โข Published Sep 15 โข 27
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models Paper โข 2310.07712 โข Published Oct 11, 2023 โข 1
Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models Paper โข 2312.02969 โข Published Dec 5, 2023 โข 15