Self-verification for LLMs.
[ICLR 2026] Official code for paper: TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning.
LLM-Based Textual Verifier using Chain-of-Thought, Variant Generation, and Majority Voting.
Measure and prevent fake work in Claude Code sessions. 3-layer defense (memory feedback + Stop hook + slash command) + 4 audit tools. Baseline: 24.91% loose / 8.28% strict fake work rate across 813 real sessions.
Do Large-scale Language Models Eliminate the Need for Domain-Specificity in Automatic Term Extraction?
Independent verification framework for AI coding agents — closes the self-certification gap by spawning a fresh LLM session that has never seen the build context.
Add a description, image, and links to the self-verification topic page so that developers can more easily learn about it.
To associate your repository with the self-verification topic, visit your repo's landing page and select "manage topics."