ConceptioArchivearXiv (OAI Expanded)
arXiv (OAI Expanded)open access

Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback

Krasitskii, Mikhail et al.
arXiv (OAI Expanded) · Papers · License: Open Access
Open Source ↗Direct PDF ↓
computation and language
This document is indexed with metadata only — full text is not available in the archive for this record. Open the official source ↗
Record · ID 616189
Retrieved via Conceptio — every document is proof-bundled with source, license, and retrieval metadata.