Imagen de Portada

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ge, Yubin, Kirtane, Neeraja, Peng, Hao, Hakkani-Tür, Dilek
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Language Steering for Multilingual In-Context Learning
por: Kirtane, Neeraja, et al.
Publicado: (2026)

Do LLMs Encode Functional Importance of Reasoning Tokens?
por: Singh, Janvijay, et al.
Publicado: (2026)

Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration
por: Kargupta, Priyanka, et al.
Publicado: (2026)

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
por: Agarwal, Ishika, et al.
Publicado: (2025)

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
por: Dongre, Vardhan, et al.
Publicado: (2026)

MathRobust-LV: Evaluation of Large Language Models' Robustness to Linguistic Variations in Mathematical Reasoning
por: Kirtane, Neeraja, et al.
Publicado: (2025)

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
por: Alnuhait, Deema, et al.
Publicado: (2024)

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
por: Wahed, Muntasir, et al.
Publicado: (2025)

Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling
por: Dey, Suvodip, et al.
Publicado: (2025)

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
por: Kazi, Taaha, et al.
Publicado: (2024)

Question Generation for Assessing Early Literacy Reading Comprehension
por: Yang, Xiaocheng, et al.
Publicado: (2025)

Simulating User Agents for Embodied Conversational-AI
por: Philipov, Daniel, et al.
Publicado: (2024)

From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems
por: Rabbani, Parisa, et al.
Publicado: (2025)

Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
por: Bozdag, Nimet Beyza, et al.
Publicado: (2025)

Language Specific Knowledge: Do Models Know Better in X than in English?
por: Agarwal, Ishika, et al.
Publicado: (2025)

Confidence Estimation for LLM-Based Dialogue State Tracking
por: Sun, Yi-Jyun, et al.
Publicado: (2024)

Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs
por: Mukherjee, Sagnik, et al.
Publicado: (2025)

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
por: Mehri, Shuhaib, et al.
Publicado: (2025)

ReasoningFlow: Semantic Structure of Complex Reasoning Traces
por: Lee, Jinu, et al.
Publicado: (2025)

A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality
por: Agarwal, Ishika, et al.
Publicado: (2026)

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging
por: Kargupta, Priyanka, et al.
Publicado: (2024)

Aligning LLMs with Individual Preferences via Interaction
por: Wu, Shujin, et al.
Publicado: (2024)

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
por: Dongre, Vardhan, et al.
Publicado: (2024)

Goal Alignment in LLM-Based User Simulators for Conversational AI
por: Mehri, Shuhaib, et al.
Publicado: (2025)

Self-Improving LLM Agents at Test-Time
por: Acikgoz, Emre Can, et al.
Publicado: (2025)

Unsupervised Human Preference Learning
por: Shashidhar, Sumuk, et al.
Publicado: (2024)

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
por: Dongre, Vardhan, et al.
Publicado: (2026)

User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
por: Hao, Yuren, et al.
Publicado: (2026)

ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation
por: Ortiz-Barajas, Jesus-German, et al.
Publicado: (2026)

DocCHA: Towards LLM-Augmented Interactive Online diagnosis System
por: Liu, Xinyi, et al.
Publicado: (2025)

YourBench: Easy Custom Evaluation Sets for Everyone
por: Shashidhar, Sumuk, et al.
Publicado: (2025)

Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions
por: Jang, Jihyoung, et al.
Publicado: (2025)

TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
por: Acikgoz, Emre Can, et al.
Publicado: (2025)

From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents
por: Tiwary, Nalin, et al.
Publicado: (2024)

ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
por: Zhang, Yifei, et al.
Publicado: (2026)

Dialog Flow Induction for Constrainable LLM-Based Chatbots
por: Agrawal, Stuti, et al.
Publicado: (2024)

MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
por: Dongre, Vardhan, et al.
Publicado: (2025)

From Documents to Segments: A Contextual Reformulation for Topic Assignment
por: Yoon, Hoonsang, et al.
Publicado: (2026)

SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
por: Acikgoz, Emre Can, et al.
Publicado: (2025)

ReIn: Conversational Error Recovery with Reasoning Inception
por: Kim, Takyoung, et al.
Publicado: (2026)