2606.10298v1 Jun 09, 2026 cs.AI

From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs

Yan Wang
Yan Wang
Citations: 10
h-index: 2
Taiqiang Wu
Taiqiang Wu
The University of Hong Kong
Citations: 405
h-index: 12
Longtao Huang
Longtao Huang
Citations: 31
h-index: 2
Bin Zhu
Bin Zhu
Citations: 132
h-index: 5
Runze Jiang
Runze Jiang
Citations: 14
h-index: 2

When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reliability bottleneck. Existing contrastive decoding methods follow a \emph{context-aware} paradigm that unilaterally amplifies context over parametric priors, overwriting correct priors when the context is erroneous. We generalize this to the \textbf{conflict-aware} paradigm that dynamically allocates authority between prior and context based on conflict signals, rather than presupposing context trustworthiness. We show that the affine combination of prior and context logits yields a \textbf{power family} with an inherent \textbf{regime asymmetry}: extrapolation amplifies errors unboundedly when the prior is correct, interpolation under-corrects when the context is correct, and no static regime covers both. Existing contrastive decoding methods are instances of this family, mostly extrapolative. To evaluate both conflict directions, we propose TriState-Bench, a model-aware evaluation protocol that calibrates per-model prior knowledge to measure three conflict states: correction, resistance, and agreement. To resolve the asymmetry, we propose Adaptive Regime Routing (ARR), which routes between regimes at each step, lifting resistance EM from below 6 to 16--33 without sacrificing correction or agreement. Our code is available at https://github.com/keith-Jiang/conflict-aware-decoding.

0 Citations
0 Influential
29.4657359028 Altmetric
147.3 Score
Original PDF
1

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!