Hallucination
9 items across the graph — tagged with Hallucination.
From the graph · 9
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Glo…
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection
AI context optimization platform for files, conversations, RAG, code, logs and AI agents with context compression, evidence preservation, content-addressed reco…
Last-night exam-cram coach as a Claude Agent Skill: turns your slides, notes and past papers into a chaptered knowledge base + quiz bank, teaches only what's in…
Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
开源终端 AI 编程 Agent：以在线 Evidence Runtime 验证链（LLM 输出是 Claim、工具结果才是 Evidence）为核心。SWE-bench_Lite 官方评测 40.0% 实例级通过率（同模型 A/B +6.7pp，可复现报告）。7 种推理范式、MCP 工具、落盘补救与验证闭环。Pyth…
Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.