Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Weixin, Qu, Bowen, Xiong, Juming, Ni, Congning, Malin, Bradley A., Yin, Zhijun
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

Multi-LLM Text Summarization
by: Fang, Jiangnan, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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