In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration

arXiv:2510.00777 · cs.LG · Submitted 2025-10-01 · Read on arXiv

cs.LG

Submitted: 2025-10-01

Updated: 2026-10-27

Comments: EMNLP2026, Outstanding Paper

License: http://creativecommons.org/licenses/by/4.0/

The gist: LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feedback aimed at fixing them.

Terminology

Abstract

LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feedback aimed at fixing them. We propose in-place feedback, an interaction paradigm in which the user directly edits the model's previous response and the model continues generation from the edited context. In-place feedback consistently outperforms standard multi-turn feedback across five reasoning-intensive benchmarks while requiring fewer tokens, and our fine-grained analysis shows that it applies corrections more reliably and propagates them to subsequent reasoning. A user study with domain experts refining LLM-generated summaries corroborates these findings: participants report higher final-output satisfaction and substantially lower fatigue with in-place feedback, and a mixed strategy combining in-place and multi-turn feedback improves every dimension we measure. These results suggest that editing errors in place is a more reliable way to incorporate expert corrections than multi-turn feedback, while combining the two acts complementarily to form a more effective collaboration than either mechanism alone.

Sources

Related papers