The paper presents MIST, a four-condition benchmark for measuring language models' selective trust of context, and SCOPE, a DPO-based training method that reduces misleading-signal susceptibility without hurting clean, correct-context, or irrelevant-context accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning When to Trust via Selective Context Preference Optimization
The paper presents MIST, a four-condition benchmark for measuring language models' selective trust of context, and SCOPE, a DPO-based training method that reduces misleading-signal susceptibility without hurting clean, correct-context, or irrelevant-context accuracy.