No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation
Year: 2026
Type: conference-paper
Abstract: Large language models (LLMs) can answer questions and summarize documents when conditioned on external contexts (e.g., retrieved evidence), yet context use remains unreliable: models may overwrite an already-correct output (neutral regression) even when the context is non-informative.We formalize neutral regression as a do-no-harm requirement and quantify it by measuring accuracy drops on baseline-correct items under answer-consistent contexts.We propose No-Worse Context-Aware Decoding (NWCAD), a decode-time adapter built on a two-stream setup with a twostage gate: it backs off to no-context decoding when the context is non-informative, and otherwise uses context-conditioned decoding with a CAD-style fallback under uncertainty.We evaluate NWCAD on benchmarks that separate do-no-harm reliability from context utilization (accuracy gains on genuinely helpful contexts).NWCAD prevents neutral regression on baseline-correct items while preserving strong context-driven accuracy on helpful contexts.
Authors: Yufei Tao, Ameeta Agrawal
Institution: Portland State University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166868610