惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

S
Schneier on Security
D
Docker
I
InfoQ
IT之家
IT之家
MyScale Blog
MyScale Blog
aimingoo的专栏
aimingoo的专栏
WordPress大学
WordPress大学
The Cloudflare Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Recorded Future
Recorded Future
Recent Announcements
Recent Announcements
博客园 - 聂微东
美团技术团队
U
Unit 42
Scott Helme
Scott Helme
Stack Overflow Blog
Stack Overflow Blog
P
Privacy & Cybersecurity Law Blog
V
Vulnerabilities – Threatpost
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
L
Lohrmann on Cybersecurity
H
Help Net Security
博客园 - 叶小钗
阮一峰的网络日志
阮一峰的网络日志
T
The Blog of Author Tim Ferriss
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
C
Cybersecurity and Infrastructure Security Agency CISA
H
Hackread – Cybersecurity News, Data Breaches, AI and More
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Google Online Security Blog
Google Online Security Blog
D
DataBreaches.Net
F
Fortinet All Blogs
V
V2EX - 技术
S
SegmentFault 最新的问题
云风的 BLOG
云风的 BLOG
C
Cisco Blogs
Hacker News - Newest:
Hacker News - Newest: "LLM"
AI
AI
L
LINUX DO - 热门话题
Martin Fowler
Martin Fowler
S
Security Affairs
O
OpenAI News
E
Exploit-DB.com RSS Feed
Microsoft Security Blog
Microsoft Security Blog
C
Check Point Blog
The Hacker News
The Hacker News
博客园_首页
Cloudbric
Cloudbric
Project Zero
Project Zero
J
Java Code Geeks
T
Tenable Blog

cs.CL updates on arXiv.org

Does Topic Sentiment Cause Perceived Ideology? Comparing Human and LLM Annotations in Political News Articles Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces Re-Centering Humans in LLM Personalization UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning CAF-Gen: A Multi-Agent System for Enriching Argumentation Structures The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment What Do People Actually Want From AI? Mapping Preference Plurality HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule Signal-Driven Observation for Long-Horizon Web Agents Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation Modular Monolingual Adaptation using Pretrained Language Models When to Think Deeply: Inhibitory Deliberation for LLM Reasoning PromptPrint: Behavioral Biometrics Through Natural Language Prompting in LLMs When Better Codebooks Are Not Enough: Predictive Performance and Behavioral Reliability in LLM Political Event Coding A Four-Condition Diagnostic Protocol for Evidence Utilization in Long-Context and Retrieval-Augmented Language Models Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responses Korean Culture into LLM Alignment: Toward Cultural Coherence Quantifying Media Representation Dynamics Across 25 Years of News Reporting on Policing-related Deaths Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning The Dark Regulome: Disentangling Predictability from Regulation in Genomic Foundation Models CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification Interpreting Brain Responses to Language with Sparse Features from Language Models Are Large Language Models Suitable for Graph Computation? Progress and Prospects An Expanded Synthetic Conversation Dataset for Multi-Turn Smishing Detection EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering Epidemiology of Model Collapse: Modeling Synthetic Data Contamination via Bilayer SIR Dynamics Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO Generic Triple-Latent Compression with Gated Associative Retrieval PEFT of SLM for Telecommunications Customer Support: A Comparative Study of LoRA Configurations with Energy Consumption Analysis MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment Multi-Granularity Reasoning for Natural Language Inference LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models LoRi: Low-Rank Distillation for Implicit Reasoning A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing Self-supervised User Profile Generation for Personalization Trajectory Dynamics in Language Model Hidden States Predict Human Processing Costs Beyond Surprisal ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval ComplexityMT: Benchmarking the Interaction Between Text Complexity and Machine Translation Multilingual Coreference Resolution via Cycle-Consistent Machine Translation Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution MASF: A Multi-Model Adaptive Selection Framework for Abstractive Text summarization CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning Multilingual Detection of Alzheimer's Disease from Speech: A Cross-Linguistic Transfer Learning Approach ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization Using Large Language Models to Support High Volume Application Review for an Undergraduate Research Program Domain-Aware Mispronunciation Detection and Diagnosis Using Language-Specific Statistical Graphs TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training What's in a Name? Morphological Shortcuts by LLMs in Pharmacology AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints An ERP Study on Recursive Locative Processing in Mandarin-Speaking Children with Autism When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer Bootstrapping Semantic Layer from Execution for Text-to-SQL QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models Rethinking LoRA Memory Through the Lens of KV Cache Compression Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems Interpreting Style Representations via Style-Eliciting Prompts Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement Can LLMs Be Constrained to the Past? Improving Knowledge Cutoff through Recall-Based Prompting ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads Would you still call this Dax? Novel Visual References in VLMs and Humans Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs Forgive or forget: Understanding the context of hate in audio retrieval systems ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization Analysis of the Neglect-Zero Effect in Large Language Models YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents Representing Research Attention as Contextually Structured Flows Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version) ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach To Be Multimodal or Not to Be: Query-Adaptive Audio-Visual Person Retrieval via Active Modality Detection Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails Large Language Models are Perplexed by some Political Parties Measuring the sensitivity of LLM-based structured extraction to prompt, model, and schema choices in clinical discharge summaries Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems The Generator-Eraser Paradox: Community Guidelines for Responsible LLM-Assisted Dialect Resource Creation Contextualized Prompting For Stance Detection On Social Media
TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication
[Submitted on 5 Jun 2026] · 2026-06-08 · via cs.CL updates on arXiv.org

View PDF HTML (experimental)

Abstract:Retrieval-augmented generation (RAG) successfully grounds large language model (LLM) outputs in trusted documents, but factual grounding alone is insufficient for sensitive peer-support health communication. In domains such as HIV peer support, responses must also be accessible, stigma-free, empathetic, and tailored to the recipient. This paper presents TA-RAG, a lightweight, prompt-based tone-aware RAG framework that embeds explicit tone control into a RAG pipeline without requiring model fine-tuning. We operationalise tone across four core components: stigma-free rewriting, readability adjustment, recipient adaptation, and empathy rephrasing. We evaluate TA-RAG through component-level tests using questions derived from HIV Online Learning Australia (HOLA), UNAIDS terminology guidance, readability metrics, peer-support standards from National Association of People with HIV Australia (NAPWHA), and a public empathy dataset. Results show that the TA-RAG's components improve their targeted communication quality while preserving key content. These findings emphasise that prompt-based tone control is a potential direction for making RAG outputs suitable for sensitive peer-support health communication.

Submission history

From: Yong-Bin Kang [view email]
[v1] Fri, 5 Jun 2026 00:45:03 UTC (587 KB)