Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Learning When to Trust via Selective Context Preference Optimization

cs.CL · 2026-08-06 · conditional · novelty 7.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning When to Trust via Selective Context Preference Optimization cs.CL · 2026-08-06 · conditional · none · ref 9

    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.