Imagen de Portada

Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, San, Lee, Gary Geunbae
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence I.2.7
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues
por: Hua, Yuncheng, et al.
Publicado: (2024)

Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design
por: Yao, Huaiyuan, et al.
Publicado: (2025)

Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data
por: Lübbers, Christopher Lee
Publicado: (2025)

Obfuscation Rules for Detecting and Detoxifying Korean Toxicity
por: Lee, Yejin, et al.
Publicado: (2025)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
por: Saji, Alan, et al.
Publicado: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
por: Peters, Sydney, et al.
Publicado: (2025)

Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues
por: Kautsar, Muhammad Dehan Al, et al.
Publicado: (2026)

Predictive Simultaneous Interpretation: Harnessing Large Language Models for Democratizing Real-Time Multilingual Communication
por: Iida, Kurando, et al.
Publicado: (2024)

LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation
por: Yuan, Weikang, et al.
Publicado: (2025)

Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs
por: Tereshchenko, Yehor, et al.
Publicado: (2025)

Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue
por: Scantamburlo, Riccardo, et al.
Publicado: (2026)

SADAS: A Dialogue Assistant System Towards Remediating Norm Violations in Bilingual Socio-Cultural Conversations
por: Hua, Yuncheng, et al.
Publicado: (2024)

HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications
por: Xu, Weijie, et al.
Publicado: (2024)

Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers
por: Peng, Zuquan, et al.
Publicado: (2024)

A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs
por: Park, Chiwan, et al.
Publicado: (2025)

DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory
por: Zhou, Wenxuan, et al.
Publicado: (2025)

Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation
por: Cacioli, Jon-Paul
Publicado: (2026)

LASTIST: LArge-Scale Target-Independent STance dataset
por: Kim, DongJae, et al.
Publicado: (2025)

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
por: Lu, Yaxi, et al.
Publicado: (2024)

Fine-Tuned Large Language Models for Logical Translation: Reducing Hallucinations with Lang2Logic
por: Pan, Muyu, et al.
Publicado: (2025)

HR-MultiWOZ: A Task Oriented Dialogue (TOD) Dataset for HR LLM Agent
por: Xu, Weijie, et al.
Publicado: (2024)

USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task
por: Li, Jianjian, et al.
Publicado: (2024)

Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
por: Xu, Shuyao, et al.
Publicado: (2025)

Machine Unlearning for Masked Diffusion Language Models
por: Lee, Georu, et al.
Publicado: (2026)

Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
por: Wu, Shuai, et al.
Publicado: (2026)

SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
por: Kim, Seoyeon, et al.
Publicado: (2026)

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
por: Le, Linh, et al.
Publicado: (2026)

From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
por: Wang, Xinyue, et al.
Publicado: (2026)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
por: Oketunji, Abiodun Finbarrs
Publicado: (2023)

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
por: Gu, Yu, et al.
Publicado: (2024)

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
por: Siegel, Noah Y., et al.
Publicado: (2025)

More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
por: Liu, Ming
Publicado: (2026)

Persona Inconstancy in Multi-Agent LLM Collaboration: Conformity, Confabulation, and Impersonation
por: Baltaji, Razan, et al.
Publicado: (2024)

Blessing or curse? A survey on the Impact of Generative AI on Fake News
por: Loth, Alexander, et al.
Publicado: (2024)

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

Persuasiveness and Bias in LLM: Investigating the Impact of Persuasiveness and Reinforcement of Bias in Language Models
por: Roy, Saumya
Publicado: (2025)

From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression
por: Choi, Eunseong, et al.
Publicado: (2024)

Argumentatively Coherent Judgmental Forecasting
por: Gorur, Deniz, et al.
Publicado: (2025)

Self-Emotion Blended Dialogue Generation in Social Simulation Agents
por: Zhang, Qiang, et al.
Publicado: (2024)

Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
por: Fukui, Hiroki
Publicado: (2026)