Pith. sign in

REVIEW 3 cited by

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts

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

arxiv 2405.11613 v2 pith:FTYW3VFW submitted 2024-05-19 cs.CL

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts

classification cs.CL
keywords knowledgellmsperformanceconfidencedeckeditededitingfacts
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The knowledge within large language models (LLMs) may become outdated quickly. While in-context editing (ICE) is currently the most effective method for knowledge editing (KE), it is constrained by the black-box modeling of LLMs and thus lacks interpretability. Our work aims to elucidate the superior performance of ICE on the KE by analyzing the impacts of in-context new knowledge on token-wise distributions. We observe that despite a significant boost in logits of the new knowledge, the performance of is still hindered by stubborn knowledge. Stubborn knowledge refers to as facts that have gained excessive confidence during pretraining, making it hard to edit effectively. To address this issue and further enhance the performance of ICE, we propose a novel approach termed $\textbf{De}$coding by $\textbf{C}$ontrasting $\textbf{K}$nowledge (DeCK). DeCK derives the distribution of the next token by contrasting the logits obtained from the newly edited knowledge guided by ICE with those from the unedited parametric knowledge. Our experiments consistently demonstrate that DeCK enhances the confidence of LLMs in edited facts. For instance, it improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%, demonstrating its capability to strengthen ICE in the editing of stubborn knowledge. Our work paves the way to develop the both effective and accountable KE methods for LLMs. (The source code is available at: https://deck-llm.meirtz.com)

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

    cs.AI 2026-05 unverdicted novelty 7.0

    Introduces Latent Adversarial Robustification and Rank-Constrained Subspace Learning to enable robust generalization in multimodal knowledge editing through adversarial subspace alignment.

  2. DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

    cs.AI 2026-07 conditional novelty 6.0

    Monitoring attention entropy and image-output correlation during decoding, then applying targeted contrastive corrections, reduces hallucination in multimodal LLMs without retraining.

  3. SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation

    cs.CL 2026-06 unverdicted novelty 6.0

    SHIFT reformulates neuron editing as learnable gate modulation on under 0.01% parameters to let LLMs adaptively balance contextual and parametric knowledge during RAG generation.