Image de couverture de livre

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ge, Yubin, Kirtane, Neeraja, Peng, Hao, Hakkani-Tür, Dilek
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Language Steering for Multilingual In-Context Learning
par: Kirtane, Neeraja, et autres
Publié: (2026)

Do LLMs Encode Functional Importance of Reasoning Tokens?
par: Singh, Janvijay, et autres
Publié: (2026)

Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration
par: Kargupta, Priyanka, et autres
Publié: (2026)

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
par: Agarwal, Ishika, et autres
Publié: (2025)

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
par: Dongre, Vardhan, et autres
Publié: (2026)

MathRobust-LV: Evaluation of Large Language Models' Robustness to Linguistic Variations in Mathematical Reasoning
par: Kirtane, Neeraja, et autres
Publié: (2025)

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
par: Alnuhait, Deema, et autres
Publié: (2024)

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
par: Wahed, Muntasir, et autres
Publié: (2025)

Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling
par: Dey, Suvodip, et autres
Publié: (2025)

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
par: Kazi, Taaha, et autres
Publié: (2024)

Question Generation for Assessing Early Literacy Reading Comprehension
par: Yang, Xiaocheng, et autres
Publié: (2025)

Simulating User Agents for Embodied Conversational-AI
par: Philipov, Daniel, et autres
Publié: (2024)

From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems
par: Rabbani, Parisa, et autres
Publié: (2025)

Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
par: Bozdag, Nimet Beyza, et autres
Publié: (2025)

Language Specific Knowledge: Do Models Know Better in X than in English?
par: Agarwal, Ishika, et autres
Publié: (2025)

Confidence Estimation for LLM-Based Dialogue State Tracking
par: Sun, Yi-Jyun, et autres
Publié: (2024)

Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs
par: Mukherjee, Sagnik, et autres
Publié: (2025)

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
par: Mehri, Shuhaib, et autres
Publié: (2025)

ReasoningFlow: Semantic Structure of Complex Reasoning Traces
par: Lee, Jinu, et autres
Publié: (2025)

A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality
par: Agarwal, Ishika, et autres
Publié: (2026)

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging
par: Kargupta, Priyanka, et autres
Publié: (2024)

Aligning LLMs with Individual Preferences via Interaction
par: Wu, Shujin, et autres
Publié: (2024)

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
par: Dongre, Vardhan, et autres
Publié: (2024)

Goal Alignment in LLM-Based User Simulators for Conversational AI
par: Mehri, Shuhaib, et autres
Publié: (2025)

Self-Improving LLM Agents at Test-Time
par: Acikgoz, Emre Can, et autres
Publié: (2025)

Unsupervised Human Preference Learning
par: Shashidhar, Sumuk, et autres
Publié: (2024)

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
par: Dongre, Vardhan, et autres
Publié: (2026)

User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
par: Hao, Yuren, et autres
Publié: (2026)

ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation
par: Ortiz-Barajas, Jesus-German, et autres
Publié: (2026)

DocCHA: Towards LLM-Augmented Interactive Online diagnosis System
par: Liu, Xinyi, et autres
Publié: (2025)

YourBench: Easy Custom Evaluation Sets for Everyone
par: Shashidhar, Sumuk, et autres
Publié: (2025)

Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions
par: Jang, Jihyoung, et autres
Publié: (2025)

TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
par: Acikgoz, Emre Can, et autres
Publié: (2025)

From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents
par: Tiwary, Nalin, et autres
Publié: (2024)

ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
par: Zhang, Yifei, et autres
Publié: (2026)

Dialog Flow Induction for Constrainable LLM-Based Chatbots
par: Agrawal, Stuti, et autres
Publié: (2024)

MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
par: Dongre, Vardhan, et autres
Publié: (2025)

From Documents to Segments: A Contextual Reformulation for Topic Assignment
par: Yoon, Hoonsang, et autres
Publié: (2026)

SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
par: Acikgoz, Emre Can, et autres
Publié: (2025)

ReIn: Conversational Error Recovery with Reasoning Inception
par: Kim, Takyoung, et autres
Publié: (2026)