← Search

Fumeng Yang

2 accepted papers

2025

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

EMNLP 2025

To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or evaluate (ChatbotArena) on what users prefer, assuming this reflects what helps them. We test this with Planorama: an int

Cited by 0SourcePDFScholar
2025

Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas

ACL 2025long

LLMs are aligned to follow input instructions by learning which of two responses users prefer for a prompt. However, such preference data do not convey *why* users prefer responses that are chosen or rejected, so LLMs trained on these datasets cannot tailor responses to varied user needs. To surface…