Copertina

Prism-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ge, Yuyao, Liu, Shenghua, Wang, Yiwei, Liu, Tianyu, Bi, Baolong, Mei, Lingrui, Yao, Jiayu, Guo, Jiafeng, Cheng, Xueqi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

A Survey of Vibe Coding with Large Language Models
di: Ge, Yuyao, et al.
Pubblicazione: (2025)

HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents
di: Wang, Lexin, et al.
Pubblicazione: (2026)

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

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

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

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

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
di: Bi, Baolong, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
di: Wen, Yuchen, et al.
Pubblicazione: (2024)

Bridging Queries and Tables through Entities in Table Retrieval
di: Li, Da, et al.
Pubblicazione: (2025)

MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning
di: Cui, Wanqing, et al.
Pubblicazione: (2024)

Reproducibility Analysis and Enhancements for Multi-Aspect Dense Retriever with Aspect Learning
di: Bi, Keping, et al.
Pubblicazione: (2024)

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
di: Zhang, Hengran, et al.
Pubblicazione: (2024)

Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective
di: Li, Da, et al.
Pubblicazione: (2025)

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

CIR at the NTCIR-17 ULTRE-2 Task
di: Yu, Lulu, et al.
Pubblicazione: (2023)

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

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

Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration
di: Wu, Guangxin, et al.
Pubblicazione: (2026)

Large Language Models as Computable Approximations to Solomonoff Induction
di: Wan, Jun, et al.
Pubblicazione: (2025)

Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
di: Chen, Lu, et al.
Pubblicazione: (2024)

Spectral Attention Steering for Prompt Highlighting
di: Li, Weixian Waylon, et al.
Pubblicazione: (2026)

Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance
di: Yu, Lulu, et al.
Pubblicazione: (2025)

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