Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bi, Baolong, Liu, Shenghua, Mei, Lingrui, Wang, Yiwei, Ji, Pengliang, Cheng, Xueqi
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SLANG: New Concept Comprehension of Large Language Models
by: Mei, Lingrui, et al.
Published: (2024)

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
by: Bi, Baolong, et al.
Published: (2024)

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
by: Bi, Baolong, et al.
Published: (2024)

LPNL: Scalable Link Prediction with Large Language Models
by: Bi, Baolong, et al.
Published: (2024)

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
by: Mei, Lingrui, et al.
Published: (2024)

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
by: Mei, Lingrui, et al.
Published: (2024)

Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
by: Bi, Baolong, et al.
Published: (2025)

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
by: Bi, Baolong, et al.
Published: (2024)

Not in Sync: Unveiling Temporal Bias in Audio Chat Models
by: Yao, Jiayu, et al.
Published: (2025)

a1: Steep Test-time Scaling Law via Environment Augmented Generation
by: Mei, Lingrui, et al.
Published: (2025)

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
by: Yao, Jiayu, et al.
Published: (2025)

Prism-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models
by: Ge, Yuyao, et al.
Published: (2026)

Gated Differentiable Working Memory for Long-Context Language Modeling
by: Mei, Lingrui, et al.
Published: (2026)

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
by: Ge, Yuyao, et al.
Published: (2025)

RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
by: Bi, Baolong, et al.
Published: (2025)

Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization
by: Chen, Juan, et al.
Published: (2025)

Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
by: Ge, Yuyao, et al.
Published: (2025)

Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception
by: Ni, Shiyu, et al.
Published: (2025)

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
by: Ge, Yuyao, et al.
Published: (2024)

PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
by: Bi, Baolong, et al.
Published: (2026)

How Knowledge Popularity Influences and Enhances LLM Knowledge Boundary Perception
by: Ni, Shiyu, et al.
Published: (2025)

DeepEdit: Knowledge Editing as Decoding with Constraints
by: Wang, Yiwei, et al.
Published: (2024)

Fact-Level Confidence Calibration and Self-Correction
by: Yuan, Yige, et al.
Published: (2024)

A Survey of Context Engineering for Large Language Models
by: Mei, Lingrui, et al.
Published: (2025)

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
by: Wang, Cheng, et al.
Published: (2024)

Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
by: Bi, Baolong, et al.
Published: (2025)

ALiiCE: Evaluating Positional Fine-grained Citation Generation
by: Xu, Yilong, et al.
Published: (2024)

Context-DPO: Aligning Language Models for Context-Faithfulness
by: Bi, Baolong, et al.
Published: (2024)

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
by: Ni, Shiyu, et al.
Published: (2024)

KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking
by: Lourenço, Vítor N., et al.
Published: (2026)

Stable Knowledge Editing in Large Language Models
by: Wei, Zihao, et al.
Published: (2024)

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models
by: Xu, Yilong, et al.
Published: (2025)

Reinforced Lifelong Editing for Language Models
by: Li, Zherui, et al.
Published: (2025)

MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
by: Wei, Zihao, et al.
Published: (2024)

Knowledge Graph Error Detection with Contrastive Confidence Adaption
by: Liu, Xiangyu, et al.
Published: (2023)

Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
by: Deng, Jingcheng, et al.
Published: (2024)

NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
by: Fei, Weizhi, et al.
Published: (2025)

Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory
by: Tao, Xingjian, et al.
Published: (2024)

LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs
by: Yang, Sihui, et al.
Published: (2024)

Learning to Edit: Aligning LLMs with Knowledge Editing
by: Jiang, Yuxin, et al.
Published: (2024)