Tag
This paper presents InternReviewer and InternAdvocate, a framework for developing AI agents in academic peer review and rebuttal using agentic reinforcement learning with objective rewards to improve reasoning depth, citation accuracy, and reduce hallucinations.
Stanford researchers led by James Zou found that AI models from OpenAI, Anthropic, and Google cite the wrong sources about 30% of the time, even when answers are mostly correct. The study highlights a critical mismatch between text generation and accurate citation, posing risks for fields like medicine and law.
A developer building an AI legal assistant for a German law firm details seven specific LLM citation failure modes and the prompt-engineering fixes used to meet strict legal citation standards.