🛰️ Daily AI Frontier
‹ back to 2026-07-22

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

Research LLM Agents

Merged summary

TL;DR - SelectBench trains LLMs to use valid retrieved evidence while rejecting misleading or harmful content. Reinforcement learning produced modest gains without degrading general capabilities, but did not improve prompt-injection resistance.

  • SelectBench-v2 evaluates selective evidence adoption across 325 corrected test examples.
  • DAPO post-training raised strict success from 22.46% to 25.54% with rule rewards and 26.46% with a frozen semantic judge.
  • Trained models adopted less forbidden content and generated shorter, more focused answers.
  • Gains did not survive Holm correction; MMLU and clean HotpotQA performance remained stable.

Sources (1)

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

arXiv cs.CL Yanyu Chen, Yue Li, Yongyi Cui, Dongsheng Shi, Lichang Dai 2026-07-22 arXiv:2607.20090

TL;DR - SelectBench trains LLMs to use valid retrieved evidence while rejecting misleading or harmful content. Reinforcement learning produced modest gains without degrading general capabilities, but did not improve prompt-injection resistance.

  • SelectBench-v2 evaluates selective evidence adoption across 325 corrected test examples.
  • DAPO post-training raised strict success from 22.46% to 25.54% with rule rewards and 26.46% with a frozen semantic judge.
  • Trained models adopted less forbidden content and generated shorter, more focused answers.
  • Gains did not survive Holm correction; MMLU and clean HotpotQA performance remained stable.
item →