Imagen de Portada

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Talokar, Nivya, Tarun, Ayush K, Mandal, Murari, Andriushchenko, Maksym, Bosselut, Antoine
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Revisiting Multilingual Data Mixtures in Language Model Pretraining
por: Foroutan, Negar, et al.
Publicado: (2025)

Does Refusal Training in LLMs Generalize to the Past Tense?
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs
por: Fan, Dongyang, et al.
Publicado: (2025)

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

Capability-Based Scaling Trends for LLM-Based Red-Teaming
por: Panfilov, Alexander, et al.
Publicado: (2025)

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
por: Bayazit, Deniz, et al.
Publicado: (2025)

The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units
por: AlKhamissi, Badr, et al.
Publicado: (2024)

Decomposing and Measuring Evaluation Awareness
por: Li, Changling, et al.
Publicado: (2026)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
por: Zhao, Hao, et al.
Publicado: (2024)

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
por: Golubev, Alexander, et al.
Publicado: (2025)

PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning
por: Chen, Zeming, et al.
Publicado: (2025)

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
por: Sinha, Yash, et al.
Publicado: (2024)

FutureSim: Replaying World Events to Evaluate Adaptive Agents
por: Goel, Shashwat, et al.
Publicado: (2026)

Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network
por: AlKhamissi, Badr, et al.
Publicado: (2024)

HalluHard: A Hard Multi-Turn Hallucination Benchmark
por: Fan, Dongyang, et al.
Publicado: (2026)

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
por: Li, Jiaqian, et al.
Publicado: (2026)

TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents
por: Djuhera, Aladin, et al.
Publicado: (2026)

Safety Training Persists Through Helpfulness Optimization in LLM Agents
por: Plaut, Benjamin
Publicado: (2026)

Direct Multi-Turn Preference Optimization for Language Agents
por: Shi, Wentao, et al.
Publicado: (2024)

Reliable Evaluation and Benchmarks for Statement Autoformalization
por: Poiroux, Auguste, et al.
Publicado: (2024)

LLMs Are In-Context Bandit Reinforcement Learners
por: Monea, Giovanni, et al.
Publicado: (2024)

TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data
por: Chundawat, Vikram S, et al.
Publicado: (2022)

A Unified Framework for Continual Learning and Unlearning
por: Chatterjee, Romit, et al.
Publicado: (2024)

Agents Are All You Need for LLM Unlearning
por: Sanyal, Debdeep, et al.
Publicado: (2025)

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
por: Wang, Zihan, et al.
Publicado: (2025)

ConLID: Supervised Contrastive Learning for Low-Resource Language Identification
por: Foroutan, Negar, et al.
Publicado: (2025)

QuantSightBench: Evaluating LLM Quantitative Forecasting with Prediction Intervals
por: Qin, Jeremy, et al.
Publicado: (2026)

GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters
por: Choudhary, Anand, et al.
Publicado: (2025)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
por: Xi, Zhiheng, et al.
Publicado: (2025)

LLM Assistance for Pediatric Depression
por: Ignashina, Mariia, et al.
Publicado: (2025)

Discovering Knowledge-Critical Subnetworks in Pretrained Language Models
por: Bayazit, Deniz, et al.
Publicado: (2023)

Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
por: Huang, Zixuan, et al.
Publicado: (2025)

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
por: Wei, Zhepei, et al.
Publicado: (2025)

M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models
por: Maheshwary, Rishabh, et al.
Publicado: (2024)

MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcare
por: Nigam, Shubham Kumar, et al.
Publicado: (2026)

Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models
por: Guo, Keyan, et al.
Publicado: (2024)

InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context
por: de Oliveira, Bryan L. M., et al.
Publicado: (2025)

Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
por: Hwang, Jaedong, et al.
Publicado: (2025)

Eliciting Behaviors in Multi-Turn Conversations
por: Huang, Jing, et al.
Publicado: (2025)

A Logical Fallacy-Informed Framework for Argument Generation
por: Mouchel, Luca, et al.
Publicado: (2024)