REVIEW 8 cited by
Entity-Based Knowledge Conflicts in Question Answering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at training time, and contextual, given as a passage at inference time. To understand how models use these sources together, we formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information. Analyzing the behaviour of popular models, we measure their over-reliance on memorized information (the cause of hallucinations), and uncover important factors that exacerbate this behaviour. Lastly, we propose a simple method to mitigate over-reliance on parametric knowledge, which minimizes hallucination, and improves out-of-distribution generalization by 4%-7%. Our findings demonstrate the importance for practitioners to evaluate model tendency to hallucinate rather than read, and show that our mitigation strategy encourages generalization to evolving information (i.e., time-dependent queries). To encourage these practices, we have released our framework for generating knowledge conflicts.
Forward citations
Cited by 8 Pith papers
-
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
Clinical RAG can attribute real evidence about drug Y to queried drug X at high rates under adversarial retrieval, a failure invisible to faithfulness and citation metrics but detectable by entity-attribution verification.
-
Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines
In a controlled 75,476-trial stress test, about 73% of omitted-fact failures in LLM agent pipelines are traced to deterministic middleware (redaction, pagination, truncation) rather than model behavior.
-
Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation
LLM judges frequently mark candidates wrong when the gold reference contradicts the model's own knowledge, even if the candidate exactly matches the provided reference.
-
On Mechanistic Circuits for Extractive Question-Answering
One attention head from the extracted context-faithfulness circuit provides reliable extractive QA attribution and improves context faithfulness when its attributions are added to the prompt.
-
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
A training method that injects token-level causal labels into attention improves out-of-distribution accuracy on a synthetic benchmark and slightly on math/reasoning tasks.
-
I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking
A text-first, multi-round visual feedback framework reports state-of-the-art top-1 accuracy on WikiMEL, WikiDiverse, and RichMEL.
-
Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training
Fine-tuning a 3B LLM on randomly symbolized reasoning questions reduces spurious-correlation failures and improves OOD accuracy on CLadder and PrOntoQA.
-
KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
Training RAG generators on contrastive knowledge-graph pairs with weighted DPO improves average exact-match by 1.8 to 4.2 points across three model sizes.
Discussion (0). Continue with ORCID to comment.