AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Copy-Paste to Mitigate Large Language Model Hallucinations

Yongchao Long, Yingying Zhang, Xianbin Wen, Xian Wu, Yuxi Zhou, Shenda Hong

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
DPO on 365 high-copying preference samplesLlama-3-8B · FaithEval counterfactualaccuracy: 67.1 -> 92.8Improved
DPO on 365 high-copying preference samplesLlama-3.1-8B · FaithEval counterfactualaccuracy: 65.5 -> 92.6Improved
train on high-copying preferences (original context)Mistral-7B-v0.2 · ConFiQA-MR originalaccuracy: 71.20 -> 91.87Improved
train on high-copying preferences (original context)Llama-3.1-8B · PubMedQA originalaccuracy: 98.15 -> 97.67No clear effect
CopyPasteLLM (365 samples) vs Context-DPO (18,000 seen samples)Llama-3-8B · ConFiQA-MR counterfactualaccuracy: 88.4 -> 80.9Hurt
CopyPasteLLM vs Context-DPOMistral-7B-v0.2 · ConFiQA-MC counterfactualaccuracy: 80.4 -> 82.5Improved
use CP-Order or CP-Refine prompting instead of AttributedLlama-3.1-8B-Instruct · avg of RAGTruth, FaithEval, PubMedQAfaithfulness: 70.72 -> 91.39 (CP-Order)Improved
CP-Link instead of CP-Order (ablation)Llama-3.1-8B-Instruct · avg of three datasetsfaithfulness: 91.39 -> 81.95Hurt
apply CopyPasteLLM on ambiguous (Negotiation) samplesLlama-3.1-8B · PubMedQA-Labeled Negotiationaccuracy: 46.38 -> 44.93No clear effect
apply CopyPasteLLM on clear-evidence (Consensus) samplesLlama-3-8B · PubMedQA-Labeled Consensusaccuracy: 75.49 -> 86.85Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy