Cool Papers · cs.CL (papers.cool) · RSS 摘要

信源：Cool Papers · cs.CL (papers.cool) · https://papers.cool/arxiv/cs.CL/feed

• Behavioral Couplings: From Formation to Behavioral Emergence in Language Models — Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, …
• DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses — Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We introduce an…
• Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation — A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond an…
• Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding — Speculative decoding typically characterizes speedup by draft tokens accepted per verification round. Lossless verification preserves the target model's output distribution and th…
• Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal — While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, leaving multilingual settings …