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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Choi, Youngbin, Lee, Minjong, Moon, Saemi, Cho, Seunghyuk, Chung, Chaehyeon, Park, MoonJeong, Kim, Dongwoo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917541495963648
author Choi, Youngbin
Lee, Minjong
Moon, Saemi
Cho, Seunghyuk
Chung, Chaehyeon
Park, MoonJeong
Kim, Dongwoo
author_facet Choi, Youngbin
Lee, Minjong
Moon, Saemi
Cho, Seunghyuk
Chung, Chaehyeon
Park, MoonJeong
Kim, Dongwoo
contents 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 scores highest on every measured dimension. These results suggest that editing errors directly is a more effective paradigm for expert-LLM collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00777
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
Choi, Youngbin
Lee, Minjong
Moon, Saemi
Cho, Seunghyuk
Chung, Chaehyeon
Park, MoonJeong
Kim, Dongwoo
Machine Learning
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 scores highest on every measured dimension. These results suggest that editing errors directly is a more effective paradigm for expert-LLM collaboration.
title In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
topic Machine Learning
url https://arxiv.org/abs/2510.00777