Cover Image

CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge Conflicts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Xuhua, Zhang, Richong, Nie, Zhijie
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Code-Style In-Context Learning for Knowledge-Based Question Answering
by: Nie, Zhijie, et al.
Published: (2023)

Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning
by: Zhang, Pieyi, et al.
Published: (2025)

General Table Question Answering via Answer-Formula Joint Generation
by: Wang, Zhongyuan, et al.
Published: (2025)

Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
by: Feng, Zhangchi, et al.
Published: (2024)

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
by: Feng, Zhangchi, et al.
Published: (2024)

ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
by: Wang, Chenyu, et al.
Published: (2026)

Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient
by: Li, Mingxin, et al.
Published: (2024)

When Text Embedding Meets Large Language Model: A Comprehensive Survey
by: Nie, Zhijie, et al.
Published: (2024)

SI-FACT: Mitigating Knowledge Conflict via Self-Improving Faithfulness-Aware Contrastive Tuning
by: Fu, Shengqiang
Published: (2025)

Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
by: Wu, Zhanyu, et al.
Published: (2026)

IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
by: Shi, Dan, et al.
Published: (2024)

Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
by: Jin, Zhuoran, et al.
Published: (2024)

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
by: Tan, Hexiang, et al.
Published: (2024)

Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict
by: Sun, Kaiser, et al.
Published: (2025)

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
by: Chen, Yihang, et al.
Published: (2026)

CA-BERT: Leveraging Context Awareness for Enhanced Multi-Turn Chat Interaction
by: Liu, Minghao, et al.
Published: (2024)

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
by: Su, Zhaochen, et al.
Published: (2024)

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
by: Diao, Muxi, et al.
Published: (2026)

Open Domain Question Answering with Conflicting Contexts
by: Liu, Siyi, et al.
Published: (2024)

Adaptive Rectification Sampling for Test-Time Compute Scaling
by: Tan, Zhendong, et al.
Published: (2025)

A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens
by: Nie, Zhijie, et al.
Published: (2024)

LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
by: Zheng, Yaowei, et al.
Published: (2024)

Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
by: Cao, Han, et al.
Published: (2024)

Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging
by: Li, Mingxin, et al.
Published: (2024)

Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts
by: Ma, Haodi, et al.
Published: (2025)

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
by: Nie, Ercong, et al.
Published: (2024)

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
by: Huang, Chengsong, et al.
Published: (2024)

HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models
by: Zhang, Boya, et al.
Published: (2025)

Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning
by: Nie, Zhijie, et al.
Published: (2024)

Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
by: Zhao, Tianzhe, et al.
Published: (2026)

Multimodal Contrastive In-Context Learning
by: Miyanishi, Yosuke, et al.
Published: (2024)

Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation
by: Zhang, Junhao, et al.
Published: (2025)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
by: Zhang, Yunxiang, et al.
Published: (2025)

SIFT: Grounding LLM Reasoning in Contexts via Stickers
by: Zeng, Zihao, et al.
Published: (2025)

Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
by: Zhou, Yueer, et al.
Published: (2025)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
by: Zhou, Yigeng, et al.
Published: (2026)

Conflict-Aware Soft Prompting for Retrieval-Augmented Generation
by: Choi, Eunseong, et al.
Published: (2025)

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
by: Yang, Rui, et al.
Published: (2024)

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
by: Wang, Jianing, et al.
Published: (2023)

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
by: Zhang, Zhenliang, et al.
Published: (2025)