ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning

ACL ARR 2025 May Submission4225 Authors

Abstract: Fine-tuning multi-turn dialogue systems requires high-quality supervision but often suffers from degraded performance when exposed to low-quality data. Supervision errors in early turns can propagate across subsequent turns, undermining coherence and response quality. Existing methods typically address data quality via static prefiltering, which decouples quality control from training and fails to mitigate turn-level error propagation. In this context, we propose ReSURE (REgularizing Supervision UnREliability), an adaptive learning method that dynamically down-weights unreliable supervision without explicit filtering. ReSURE estimates per-turn loss distributions using Welford’s online statistics and reweights sample losses on the fly accordingly. Experiments on both single-source and mixed-quality datasets show improved stability and response quality. Notably, ReSURE enjoys positive Spearman correlations (0.21 $\sim$ 1.0 across multiple benchmarks) between response scores and number of samples regardless of data quality, which potentially paves the way for utilizing large-scale data effectively.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: dialogue system, multi-turn dialogue, fine-tuning, Supervision Noise

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 4225