esg-report-rag-question-answering-retrieval-held-fixed-single-top-1 CLM-0384observationsingle paperReviewed by AI
In ESG-report RAG question answering with retrieval held fixed at a single top-1 chunk, open-weight 2B-30B generators vary widely in how well they stay anchored to the retrieved passage (faithfulness 0.607-0.822) yet all land in a narrow low band of factual correctness (0.387-0.449), and the most faithful model is the least factually correct, so groundedness to context and correctness of extracted ESG facts do not track each other.
Capability: Competence in a specialist domain
Observed on
Seven Ollama-served open models 2B-30B, 498 EU ESG reports, 100 synthetic QA pairs generated and judged by qwen3:4b-instruct, top-k=1 retrieval, RAGAS metrics, no retrieval ablatio.
Sources
- Measured: seven models x 100 QA pairs on seven RAGAS metrics. Weak design: judge and dataset generator are the same model as one evaluated model (authors flag self-enhancement), evaluation set is a deterministic 100-item prefix, decoding parameters not normalised across models, no confidence intervals, and single retrieval configuration so the low factual-correctness band may be a retrieval ceiling rather than a knowledge gap.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- When an LLM judge is given a prior evaluation score as context metadata on a revision, its rubric scores shift toward that uninformative prior — seven of eight tested models (API and open-weight, 0-5 scale, 20 fixed texts) show a negative total shift, and on a categorical compliance task the metadata blocks 48% of error corrections and flips about 10% of previously correct judgments to the anchored wrong label.Judging another's work as well as a careful reviewer would · reviewed by AI
- 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 · reviewed by AI
- When injecting new or counterfactual facts into a 3-4B instruct model by post-training, supervised fine-tuning on extracted QA pairs binds facts to their training question form — recall of the single fact stays reasonable while multi-source and inferential questions over the same facts collapse — and adding more SFT epochs does not close the gap, whereas mixed-policy RL that supplies the golden answer as an off-policy trajectory when on-policy rollouts fail recovers much of the generalization.Absorbing and flexibly using new knowledge · reviewed by AI
- On long-context tasks over 8K-128K-token documents in the six official UN languages, models answer word-level span questions well (about 73% average accuracy across 12 models) but degrade sharply as the required unit coarsens to sentence selection (about 21%), paragraph filling and document-level summarization and translation, so long-context competence measured by needle-style word retrieval overstates comprehension of larger discourse units.Losing information in long inputs · reviewed by AI
- When claim-level uncertainty is estimated from a response-claim graph, anchoring the graph with trusted external priors (edges weighted by entailment from verified source sections) and scoring claims by weighted closeness centrality separates ungrounded claims from repeatedly-generated-but-false ones better than internal-consistency centrality alone, and yields retrieval whose answerability tracks its accuracy instead of the near-100% answer rate GraphRAG shows on the same long documents.Stating false facts confidently · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: low. Falsifier as drafted: On the same corpus with an independent judge and a larger evaluation set, faithfulness and factual correctness rank models in the same order, or factual correctness spreads as widely as faithfulness across models.