training-model-decide-when-retrieve-critique-whether-passagesmechanismsingle paper
Training the model to decide when to retrieve and to critique whether passages support its output improves factuality and citation accuracy.
Capability: Checking claims against evidence
Sources
- Training the model to decide when to retrieve and to critique whether passages support its output improves factuality and citation accuracy.
Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.
Related claims
- Grounding generation in retrieved documents improves factual accuracy on knowledge-intensive tasks.Stating false facts confidently
- Models readily adopt a single counter-memory passage when it is coherent, and when sources conflict they follow the majority and show confirmation bias toward their own beliefs.Checking claims against evidence
- Where a passage sits in a long input changes how much the model uses it — accuracy is highest when the needed information is at the very start or the very end and lowest when it is in the middle — so ordering retrieved passages to put the most relevant ones first is a real lever on accuracy.Losing information in long inputs · contested
- When retrieval for a summarization task pulls definitions by surface term match from a general encyclopedia, ambiguous terms fetch the wrong sense and the model incorporates that unsupported background into its output, lowering claim-level factuality below the no-retrieval baseline even when the prompt tells it to ignore unrelated retrieved content.Stating false facts confidently · unreviewed
- General-purpose factuality verifiers (entailment-, consistency-, and RAG-trained) and zero-shot frontier LLM judges perform near chance at spotting unsupported claims in scientific peer reviews that must be checked against the full submitted paper, because they cannot separate paper-unsupported assertions from legitimate evaluative critique; small models fine-tuned on in-domain examples beat them by a wide margin.Stating false facts confidently · unreviewed