1
Show HN: Muteval – mutation testing for your LLM evals
变异测试一招揪出LLM评测漏洞，Muteval让评估数据更可靠，开源免费直接上手。
Article URL: https://github.com/AshwinUgale/muteval Comments URL: https://news.ycombinator.com/item?id=49388918 Points: 1 # Comments: 0
2
本周赛博领鸡蛋（7.31~8.6）：孤狼 OTXO、寻日之旅、变异小镇
本周 Epic Games 限免共带来 2 款电脑游戏与 1 款手机游戏，分别是《孤狼 OTXO》《寻日之旅 / Sol Cesto》《变异小镇 / Mutazione》。其中《OTXO》是一款俯视角动作射击游戏，《Sol Cesto》是一款回合制解谜冒险游戏，《Mutazione》则是一款偏叙事体
3
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
揭秘共享词汇任务表征如何解释LLM行为变异，为理解大模型行为差异提供新理论框架
arXiv:2604.22027v2 Announce Type: replace-cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensiti…
4
Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment
最新论文提出通过logit空间对比对齐实现跨模态生物语言模型，提升序列设计与变异评分效果。
arXiv:2606.18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token …
5
A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction
用大语言模型搭建自动化流水线，破解大规模语料库的人工标注瓶颈，高效实现英语语法变异追踪。
arXiv:2510.12306v3 Announce Type: replace Abstract: As natural language corpora expand at an unprecedented rate, manual annotation remains a significa…
6
Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution
LLM驱动的程序演化中，突变缺乏变异导致收敛问题，揭示算法局限性。
arXiv:2606.05408v1 Announce Type: new Abstract: When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? W…