Copertina

Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Weixin, Qu, Bowen, Xiong, Juming, Ni, Congning, Malin, Bradley A., Yin, Zhijun
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

Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning
di: Xiong, Juming, et al.
Pubblicazione: (2026)

VERI-DPO: Evidence-Aware Alignment for Clinical Summarization via Claim Verification and Direct Preference Optimization
di: Liu, Weixin, et al.
Pubblicazione: (2026)

MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models
di: Liu, Weixin, et al.
Pubblicazione: (2026)

Catalysts of Conversation: Examining Interaction Dynamics Between Topic Initiators and Commentors in Alzheimer's Disease Online Communities
di: Ni, Congning, et al.
Pubblicazione: (2024)

It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
di: Guo, Kevin H., et al.
Pubblicazione: (2026)

Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability
di: Guo, Kevin H., et al.
Pubblicazione: (2026)

CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
di: Guo, Kevin H., et al.
Pubblicazione: (2026)

Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses
di: Hussain, Khizar, et al.
Pubblicazione: (2026)

Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses
di: Ni, Congning, et al.
Pubblicazione: (2026)

Optimizing Domain-Adaptive Self-Supervised Learning for Clinical Voice-Based Disease Classification
di: Liu, Weixin, et al.
Pubblicazione: (2026)

Enhancing Incremental Summarization with Structured Representations
di: Hwang, EunJeong, et al.
Pubblicazione: (2024)

Multi-LLM Text Summarization
di: Fang, Jiangnan, et al.
Pubblicazione: (2024)

Designing Role Vectors to Improve LLM Inference Behaviour
di: Potertì, Daniele, et al.
Pubblicazione: (2025)

When Neutral Summaries are not that Neutral: Quantifying Political Neutrality in LLM-Generated News Summaries
di: Vijay, Supriti, et al.
Pubblicazione: (2024)

A Novel LLM-based Two-stage Summarization Approach for Long Dialogues
di: Yin, Yuan-Jhe, et al.
Pubblicazione: (2024)

EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation
di: Fan, Yuchen, et al.
Pubblicazione: (2024)

LLM Sensitivity Evaluation Framework for Clinical Diagnosis
di: Yan, Chenwei, et al.
Pubblicazione: (2025)

Neutralizing Bias in LLM Reasoning using Entailment Graphs
di: Cheng, Liang, et al.
Pubblicazione: (2025)

Understanding LLM Reasoning for Abstractive Summarization
di: Yuan, Haohan, et al.
Pubblicazione: (2025)

Abstract Meaning Representation for Hospital Discharge Summarization
di: Landes, Paul, et al.
Pubblicazione: (2025)

Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
di: Braun, Joschka, et al.
Pubblicazione: (2025)

Computational Approaches to Understanding Large Language Model Impact on Writing and Information Ecosystems
di: Liang, Weixin
Pubblicazione: (2025)

From Data to Insights: Exploring Program-of-Thoughts Prompting for Chart Summarization
di: Qu, Yutong, et al.
Pubblicazione: (2026)

Language-Independent Representations Improve Zero-Shot Summarization
di: Solovyev, Vladimir, et al.
Pubblicazione: (2024)

ISQA: Informative Factuality Feedback for Scientific Summarization
di: Li, Zekai, et al.
Pubblicazione: (2024)

COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation
di: Kumar, Raghvendra, et al.
Pubblicazione: (2025)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
di: Liu, Di, et al.
Pubblicazione: (2024)

Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
di: Huang, Kung-Hsiang, et al.
Pubblicazione: (2023)

VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
di: Yao, Dingyu, et al.
Pubblicazione: (2025)

Vector-ICL: In-context Learning with Continuous Vector Representations
di: Zhuang, Yufan, et al.
Pubblicazione: (2024)

Stylistic Evolution and LLM Neutrality in Singlish Language
di: Foo, Linus Tze En, et al.
Pubblicazione: (2026)

SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency
di: Zhang, Jiaxin, et al.
Pubblicazione: (2023)

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control
di: Cyberey, Hannah, et al.
Pubblicazione: (2025)

Adaptive Self-improvement LLM Agentic System for ML Library Development
di: Zhang, Genghan, et al.
Pubblicazione: (2025)

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization
di: Lu, Yen-Ju, et al.
Pubblicazione: (2025)

Fair Abstractive Summarization of Diverse Perspectives
di: Zhang, Yusen, et al.
Pubblicazione: (2023)

ArgCMV: An Argument Summarization Benchmark for the LLM-era
di: Gurjar, Omkar, et al.
Pubblicazione: (2025)

L3iTC at the FinLLM Challenge Task: Quantization for Financial Text Classification & Summarization
di: Pontes, Elvys Linhares, et al.
Pubblicazione: (2024)

LoFiT: Localized Fine-tuning on LLM Representations
di: Yin, Fangcong, et al.
Pubblicazione: (2024)

Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents
di: Quan, Xin, et al.
Pubblicazione: (2026)