Results 241 to 250 of about 1,137,884 (305)

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Annual Meeting of the Association for Computational Linguistics
This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their information ...
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. V. Zhao, Lili Qiu, Dongmei Zhang, K. Cobbe, Vineet Kosaraju, Mo Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano   +22 more
semanticscholar   +1 more source

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

International Conference on Learning Representations, 2023
As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance.
Melanie Sclar, Yejin Choi, Yulia Tsvetkov, Alane Suhr   +3 more
semanticscholar   +1 more source

InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Annual Meeting of the Association for Computational Linguistics
Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites).
Qiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel Kang   +3 more
semanticscholar   +1 more source

Defeating Prompt Injections by Design

arXiv.org
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data.
Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan, Jamie Hayes, Nicholas Carlini, Daniel Fabian, Christoph Kern, Chongyang Shi, Andreas Terzis, F. Tramèr   +9 more
semanticscholar   +1 more source

A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

arXiv.org
Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). This approach leverages task-specific instructions, known as prompts, to enhance model efficacy
Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, S. Mondal, Aman Chadha   +5 more
semanticscholar   +1 more source

DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks

IEEE Symposium on Security and Privacy
LLM-integrated applications and agents are vulnerable to prompt injection attacks, where an attacker injects prompts into their inputs to induce attacker-desired outputs.
Yupei Liu, Yuqi Jia, Jinyuan Jia, Dawn Song, N. Gong   +4 more
semanticscholar   +1 more source

Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)

ACM Conference on Recommender Systems, 2022
For a long time, different recommendation tasks require designing task-specific architectures and training objectives. As a result, it is hard to transfer the knowledge and representations from one task to another, thus restricting the generalization ...
Shijie Geng, Shuchang Liu, Zuohui Fu, Yingqiang Ge, Yongfeng Zhang   +4 more
semanticscholar   +1 more source

StruQ: Defending Against Prompt Injection with Structured Queries

USENIX Security Symposium
Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications, which perform text-based tasks by utilizing their advanced language understanding capabilities. However, as LLMs have improved, so have the attacks against them.
Sizhe Chen, Julien Piet, Chawin Sitawarin, David Wagner   +3 more
semanticscholar   +1 more source

TopicGPT: A Prompt-based Topic Modeling Framework

North American Chapter of the Association for Computational Linguistics
Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require “reading the tea leaves” to interpret; additionally, they offer users minimal control ...
Chau Minh Pham, Alexander Miserlis Hoyle, Simeng Sun, Mohit Iyyer   +3 more
semanticscholar   +1 more source

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Neural Information Processing Systems
Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior.
Andy Zhou, Bo Li, Haohan Wang
semanticscholar   +1 more source