arXiv AI June 10, 2026 By Runze Jiang, Taiqiang Wu, Yan Wang, Bingyu Zhu, Longtao Huang

From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs

arXiv:2606. 10298v1 Announce Type: new Abstract: When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reliability bottleneck.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Jun 6

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.

By Zhe Yu, Wenpeng Xing, Tiancheng Zhao, Mohan Li, Changting Lin, Meng Han

llms rag benchmarks safety

arXiv Computation and Language

6d ago

APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation

arXiv:2605.09492v3 Announce Type: replace Abstract: Reliable text generation is critical for deploying large language models (LLMs) in real-world applications, particularly in high-stakes domains suc...

By Tianyu Zheng, Hong Wu, Jiaji Zhong

llms nlp fine-tuning benchmarks

arXiv Computation and Language

Sep 15

DecompressionLM: Deterministic, Diagnostic, and Zero-Shot Concept Graph Extraction from Language Models

arXiv:2602.00377v3 Announce Type: replace Abstract: Existing knowledge probing methods rely on pre-defined queries, limiting extraction to known concepts. We introduce DecompressionLM, a stateless fr...

By Zhaochen Hong, Jiaxuan You

llms efficiency benchmarks safety

arXiv AI

Aug 6

CARGO-VL: Counterfactual Arbitration with Risk-Constrained Group Optimization for Vision-Language Models

arXiv:2608. 04509v1 Announce Type: new Abstract: Vision-language systems combine images with retrieved text, but these sources can disagree or jointly fail to support an answer.

By De Jiang, Zhengyang Zhang, Kehong Yuan, Shaohua Ma

llms multimodal safety

arXiv Computation and Language

Sep 2

SFAD: Speculative Factuality-Aware Decoding

arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive a...

By Guanqiao Chen, Di Wang, Lijie Hu

llms reinforcement-learning safety

arXiv AI

Sep 1

DIP: Dynamic In-Context Planner For Diffusion Language Models

arXiv:2601.03199v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. Existing In-Context...

By Yang Li, Han Meng, Chenan Wang, Zhenyu Bi, Xuan Wang, Haipeng Chen

llms diffusion benchmarks

One email a morning, machine-written

Related stories

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation

DecompressionLM: Deterministic, Diagnostic, and Zero-Shot Concept Graph Extraction from Language Models

CARGO-VL: Counterfactual Arbitration with Risk-Constrained Group Optimization for Vision-Language Models

SFAD: Speculative Factuality-Aware Decoding

DIP: Dynamic In-Context Planner For Diffusion Language Models