Length Penalties Make Chain-of-Thought Less Monitorable

  • 类型:arxiv
  • 标识:2607.09786
  • 链接:https://arxiv.org/abs/2607.09786
  • 主分类:evaluation
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:Compression reduces reasoning tokens and preserves most multiple choice accuracy, while hint influence remains near baseline, in a frontier where reducing reasoning costs removes more evidence than shorter traces alone would predict.
  • OpenAlex ID:W7168276331
  • OpenAlex DOI:10.48550/arxiv.2607.09786
  • DOI:10.48550/arxiv.2607.09786
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.09786
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:长度惩罚使 Chain-of-Thought 更难被监控
  • TLDR中文:压缩可减少推理 token 并保持大部分选择题准确率,同时提示影响接近基线——在一个前沿条件下,降低推理成本移除的证据比单纯缩短轨迹所预期的更多。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-17-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]