Jingtao Xu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
Research Timeline
2026
Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
The paper introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of whether the evidence is presented in a single prompt or gradually across multiple turns.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.AIRecentMay 28, 2026
Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
Zizhuo Lin, Quanling Liu, Jinsheng Quan, Chao Zhang +5 more
The paper introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of wh…
View →