arXiv Artificial IntelligenceReference-Based Bias Detection in LLMs via Relative Representations of Hidden States
arXiv:2609.10060v1 Announce Type: new Abstract: Existing bias auditing methods typically rely on model…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2609.10060v1 Announce Type: new Abstract: Existing bias auditing methods typically rely on model…
arXiv Artificial IntelligencearXiv:2609.10055v1 Announce Type: new Abstract: Biomedical ontology normalization maps free-text expressions…
arXiv Artificial IntelligencearXiv:2609.10036v1 Announce Type: new Abstract: Large language model agents produce fluent action sequences…
arXiv Artificial IntelligencearXiv:2609.09928v1 Announce Type: new Abstract: Latent reasoning approaches enhance token-level efficiency…
arXiv Artificial IntelligencearXiv:2609.09925v1 Announce Type: new Abstract: Modern vision-language-action (VLA) policies predict a whole…
arXiv Artificial IntelligencearXiv:2609.09898v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise for…
arXiv Artificial IntelligencearXiv:2609.09885v1 Announce Type: new Abstract: This paper studies unmanned aerial vehicle (UAV)-mouted…
arXiv Artificial IntelligencearXiv:2609.09882v1 Announce Type: new Abstract: Language models fine-tuned on customer behavior can predict…
arXiv Artificial IntelligencearXiv:2609.09875v1 Announce Type: new Abstract: Existing evaluation frameworks mostly assess only one part of…
arXiv Artificial IntelligencearXiv:2609.09864v1 Announce Type: new Abstract: Affective computing has largely followed an individual-state…
arXiv Artificial IntelligencearXiv:2609.09853v1 Announce Type: new Abstract: LLM agents for enterprise systems of record cannot be…
arXiv Artificial IntelligencearXiv:2609.09815v1 Announce Type: new Abstract: Compound LLM systems often solve a coordination problem by…