Copertina

Investigating and Alleviating Harm Amplification in LLM Interactions

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guo, Ruohao, Xu, Wei, Ritter, Alan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
di: Guo, Ruohao, et al.
Pubblicazione: (2023)

How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation
di: Guo, Ruohao, et al.
Pubblicazione: (2025)

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
di: Guo, Ruohao, et al.
Pubblicazione: (2025)

Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
di: Wu, Xiaofeng, et al.
Pubblicazione: (2025)

Probabilistic Reasoning with LLMs for k-anonymity Estimation
di: Zheng, Jonathan, et al.
Pubblicazione: (2025)

Constrained Decoding for Cross-lingual Label Projection
di: Le, Duong Minh, et al.
Pubblicazione: (2024)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
di: Andriushchenko, Maksym, et al.
Pubblicazione: (2024)

Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
di: Park, Jungsoo, et al.
Pubblicazione: (2026)

Language Models can Self-Improve at State-Value Estimation for Better Search
di: Mendes, Ethan, et al.
Pubblicazione: (2025)

Having Beer after Prayer? Measuring Cultural Bias in Large Language Models
di: Naous, Tarek, et al.
Pubblicazione: (2023)

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
di: Pandey, Punya Syon, et al.
Pubblicazione: (2025)

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
di: Chehbouni, Khaoula, et al.
Pubblicazione: (2024)

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
di: Feng, Weitao, et al.
Pubblicazione: (2025)

NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification
di: Wang, Jingyuan, et al.
Pubblicazione: (2024)

Selective Neuron Amplification in Transformer Language Models
di: Akhtar, Ryyan, et al.
Pubblicazione: (2026)

Anticipatory Evaluation of Language Models
di: Park, Jungsoo, et al.
Pubblicazione: (2025)

Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs
di: Park, Jungsoo, et al.
Pubblicazione: (2025)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
di: Chan, Yik Siu, et al.
Pubblicazione: (2025)

Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation
di: Lavrouk, Anton, et al.
Pubblicazione: (2024)

LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
di: Zou, Henry Peng, et al.
Pubblicazione: (2025)

Investigating Non-Transitivity in LLM-as-a-Judge
di: Xu, Yi, et al.
Pubblicazione: (2025)

Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
di: Ren, Yi, et al.
Pubblicazione: (2024)

STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio
di: Park, Seong-Gyu, et al.
Pubblicazione: (2026)

Representation Noising: A Defence Mechanism Against Harmful Finetuning
di: Rosati, Domenic, et al.
Pubblicazione: (2024)

Harm Amplification in Text-to-Image Models
di: Hao, Susan, et al.
Pubblicazione: (2024)

A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
di: Pfohl, Stephen R., et al.
Pubblicazione: (2024)

A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens
di: Dobre, David, et al.
Pubblicazione: (2025)

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
di: Lee, Seanie, et al.
Pubblicazione: (2024)

Initial Investigation of LLM-Assisted Development of Rule-Based Clinical NLP System
di: Shi, Jianlin, et al.
Pubblicazione: (2025)

"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations
di: Dammu, Preetam Prabhu Srikar, et al.
Pubblicazione: (2024)

Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs
di: Mendu, Sai Krishna, et al.
Pubblicazione: (2025)

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
di: Yu, Yongcan, et al.
Pubblicazione: (2026)

GMTRouter: Personalized LLM Router over Multi-turn User Interactions
di: Xie, Encheng, et al.
Pubblicazione: (2025)

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
di: Sheshadri, Abhay, et al.
Pubblicazione: (2024)

SIFiD: Reassess Summary Factual Inconsistency Detection with LLM
di: Yang, Jiuding, et al.
Pubblicazione: (2024)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
di: Huang, Tiansheng, et al.
Pubblicazione: (2024)

Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
di: Yousuf, Raquib Bin, et al.
Pubblicazione: (2025)

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
di: Chan, Chi-Min, et al.
Pubblicazione: (2025)

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
di: Abdelnabi, Sahar, et al.
Pubblicazione: (2023)

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams
di: Llorente-Saguer, Isaac
Pubblicazione: (2026)