Pith. sign in

REVIEW 3 cited by

Knowledge Conflicts for LLMs: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2403.08319 v2 pith:2OR7NE4F submitted 2024-03-13 cs.CL cs.AIcs.IRcs.LG

Rongwu Xu , Zehan Qi , Zhijiang Guo , Cunxiang Wang , Hongru Wang , Yue Zhang , Wei Xu This is my paper · ORCID
classification cs.CLcs.AIcs.IRcs.LG
keywords conflictsllmsknowledgesurveyadvancingaimsanalysisapplications
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and reviewing available solutions, this survey aims to shed light on strategies for improving the robustness of LLMs, thereby serving as a valuable resource for advancing research in this evolving area.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 4 citations worldwide. Full citation record

  1. Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    LLMs identify fabricated statistics in isolation (rates 0.76-1.00) but ignore numeric validity during synthesis, relying on a methodology-register representation that transfers across domains.

  2. Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

    cs.AI 2025-06 conditional novelty 6.0 of 10

    LLM agents frequently switch correct answers after one round of misleading feedback, and the new WAFER-QA benchmark measures this with web-backed critiques.

  3. Scaling laws for activation steering with Llama 2 models and refusal mechanisms

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Activation steering with contrastive vectors becomes less effective as Llama 2 models scale from 7B to 70B parameters, with peak effect at roughly 40% of the model's layers.

Pith tools