1
Show HN: Aevros .... A kernel that explains itself
一个从零写起的开源内核，最大亮点是崩溃时能解释自己出错的原因，让调试不再靠猜
Article URL: https://github.com/Mobeen0119/Aevros Comments URL: https://news.ycombinator.com/item?id=49142156 Points: 2 # Comments: 0
2
Training Large Language Models for Self-Explanation Faithfulness
用强化学习直接优化大模型自解释的忠实性，让AI的推理更可信。
arXiv:2607.21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explan…
3
Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
大模型自解释的可信度会随规模变化？75个模型横评揭示反事实一致性规律，看懂LLM解释的可靠性边界
arXiv:2503.13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausibl…