Blog
LLMs & Texto
Right Knowledge, Wrong Answer: Test-Time Steering for Temporal Fact Conflicts in Open-Weight Language Models
arXiv:2606.20959v1 Announce Type: new Abstract: Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdated answer. We formalize this problem as Parametric Temporal Conflict (PTC) and introduce Temporal Attractor Steering (TAS), a three-stage test-time intervention that detects likely conflicts, identifies a conflict-critical layer, and steers hidden states toward newer-fact representations without retr...
arXiv cs.LG
·Elias Hossain, Sourav Saha, Umesh Chandra Biswas, Sanjeda Sara Jennifer
·
// relacionados
Leia também
Blog
How Businesses Are Building Specialized AI They Can Trust
Blog
Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates
Blog
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
Blog