Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection · HackerPapers discussions

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection — mentioned by spmurrayzzz

Fri, 21 Nov 2025 16:53:28 GMT

There is an older paper on something related to this [1], where the model outputs reflection tokens that either trigger retrieval or critique steps. The idea is that the model recognizes that it needs to fetch some grounding subsequent to generating some factual content. Then it reviews what it previously generated with the retrieved grounding. The problem with this approach is that it does not generalize well at all out of distribution. I'm not aware of any follow up to this, but I do think it's an interesting area of research nonetheless. [1] https://arxiv.org/abs/2310.11511

Paper and discussion history. A mention is not an endorsement.

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection — mentioned by spmurrayzzz

Fri, 14 Mar 2025 20:25:22 GMT

> i.e there isn't a "I don't have enough information" option. This is true in terms of default mode for LLMs, but there's a fair amount of research dedicated to the idea of training models to signal when they need grounding. SelfRAG is an interesting, early example of this [1]. The basic idea is that the model is trained to first decide whether retrieval/grounding is necessary and then, if so, after retrieval it outputs certain "reflection" tokens to decide whether a passage is relevant to answer a user query, whether the passage is supported (or requires further grounding), and whether the…

Paper and discussion history. A mention is not an endorsement.