28 citations · 82 across the 33 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback
Mikhail Krasitskii, Alexander Gelbukh, Olga Kolesnikova +1
Reinforcement learning with human feedback (RLHF) aligns LLMs with human preferences, improving summarization fluency and safety, but causes sentiment drift: overly neutral summari…
cs.CL2026
Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance
Mikhail Krasitskii, Alexander Gelbukh, Olga Kolesnikova +1
Reinforcement Learning from Human Feedback (RLHF) has significantly improved the quality and fluency of large language models in text summarization. However, its impact on affectiv…