arXiv:2506.01937v2 Announce Type: replace
Abstract: Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, rea…
arXiv:2604.21897v1 Announce Type: new
Abstract: Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliame…
arXiv:2604.21901v1 Announce Type: new
Abstract: As model sizes continue to grow, parameter-efficient fine-tuning has emerged as a powerful alternative to full fine-tuning. While LoRA is widely adopted among these methods, recent research has explored …
arXiv:2604.21928v1 Announce Type: new
Abstract: Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perce…
arXiv:2601.13690v2 Announce Type: replace
Abstract: Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face notable challenges, including high maintenance costs and low generalization capability. …
arXiv:2603.27820v2 Announce Type: replace
Abstract: Clinical diagnosis is a complex reasoning process in which clinicians gather evidence, form hypotheses, and test them against alternative explanations. In medical training, this reasoning is explicit…
arXiv:2604.10079v3 Announce Type: replace
Abstract: Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after convergence, models ofte…
arXiv:2509.23649v2 Announce Type: replace-cross
Abstract: Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, its potential is fundamentally constrained by the …
arXiv:2512.05591v2 Announce Type: replace-cross
Abstract: Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, w…
arXiv:2604.21308v1 Announce Type: cross
Abstract: Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user’s behalf, also creates new risks for sensitive i…