Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation Paper β’ 2510.02306 β’ Published Oct 2 β’ 3
WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers Paper β’ 2509.10452 β’ Published Sep 12 β’ 2
Lost in Embeddings: Information Loss in Vision-Language Models Paper β’ 2509.11986 β’ Published Sep 15 β’ 28
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models Paper β’ 2310.07712 β’ Published Oct 11, 2023 β’ 1
Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models Paper β’ 2312.02969 β’ Published Dec 5, 2023 β’ 15