WikiChat
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
- 1.6k
- Python
- Apache-2.0
- 10 mo ago
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
Code for the EMNLP 2024 paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"
[ACL 2026] KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.
Code and data for the ACL 2024 Findings paper "Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning"
A benchmark for epistemic arbitration and misinformation resistance in AI agents. Evaluates an agent's ability to distinguish independent evidence from coordinated repetition and manufactured consensus within synthetic social environments.
Linear probes on Llama 3.1 8B hidden states rank claim correctness better than the model's stated confidence; legal QA and biography probes, Modal runs. Write-up: casella.dev/blog_interp.html