Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification Paper โข 2608.14929 โข Published Aug 14 โข 18
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper โข 2608.16859 โข Published Aug 17 โข 122
view article Article ๐๐๐ฑ๐ด๐ถ๐ป๐ด ๐๐ต๐ฒ ๐๐๐ฑ๐ด๐ฒ๐: ๐๐๐ฎ๐น๐๐ฎ๐๐ถ๐ป๐ด ๐๐น๐ถ๐ด๐ป๐บ๐ฒ๐ป๐ ๐ฎ๐ป๐ฑ ๐ฉ๐๐น๐ป๐ฒ๐ฟ๐ฎ๐ฏ๐ถ๐น๐ถ๐๐ถ๐ฒ๐ ๐ถ๐ป ๐๐๐ ๐-๐ฎ๐-๐๐๐ฑ๐ด๐ฒ๐ singh96aman โข Jun 24, 2024 โข 2
Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges Paper โข 2406.12624 โข Published Jun 18, 2024 โข 37