English
Related papers

Related papers: LLM Lies: Hallucinations are not Bugs, but Feature…

200 papers

Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user…

Computation and Language · Computer Science 2022-11-18 Fábio Perez , Ian Ribeiro

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Cryptography and Security · Computer Science 2024-12-10 Bryan Li , Sounak Bagchi , Zizhan Wang

Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. However, the specific manifestations of…

Computation and Language · Computer Science 2026-04-20 Renfei Dang , Peng Hu , Zhejian Lai , Changjiang Gao , Min Zhang , Shujian Huang

Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially when a user query includes one or more false premises-claims…

Computation and Language · Computer Science 2026-02-18 Yuehan Qin , Shawn Li , Yi Nian , Xinyan Velocity Yu , Yue Zhao , Xuezhe Ma

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

Driven by the rapid advancements of Large Language Models (LLMs), LLM-based agents have emerged as powerful intelligent systems capable of human-like cognition, reasoning, and interaction. These agents are increasingly being deployed across…

Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of hallucinations driven…

Computation and Language · Computer Science 2025-11-24 Shaowen Wang , Yiqi Dong , Ruinian Chang , Tansheng Zhu , Yuebo Sun , Kaifeng Lyu , Jian Li

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

Cryptography and Security · Computer Science 2023-05-08 Kai Greshake , Sahar Abdelnabi , Shailesh Mishra , Christoph Endres , Thorsten Holz , Mario Fritz

Despite significant ongoing efforts in safety alignment, large language models (LLMs) such as GPT-4 and LLaMA 3 remain vulnerable to jailbreak attacks that can induce harmful behaviors, including through the use of adversarial suffixes.…

Cryptography and Security · Computer Science 2024-12-20 Wei Zhao , Zhe Li , Yige Li , Jun Sun

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

Large Language Models (LLMs) have the tendency to hallucinate, i.e., to sporadically generate false or fabricated information. This presents a major challenge, as hallucinations often appear highly convincing and users generally lack the…

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Cryptography and Security · Computer Science 2026-03-18 Ali Raza , Gurang Gupta , Nikolay Matyunin , Jibesh Patra

Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations. A significant type of this issue is the false premise hallucination, which we define as the phenomenon when LLMs generate…

Computation and Language · Computer Science 2024-03-01 Hongbang Yuan , Pengfei Cao , Zhuoran Jin , Yubo Chen , Daojian Zeng , Kang Liu , Jun Zhao

Large Language Models (LLMs) have become increasingly important in natural language processing, enabling advanced data analytics through natural language queries. However, these models often generate "hallucinations"-inaccurate or…

Computation and Language · Computer Science 2024-10-29 Mikhail Rumiantsau , Aliaksei Vertsel , Ilya Hrytsuk , Isaiah Ballah

Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite advances in alignment and instruction tuning, LLMs can still…

Computation and Language · Computer Science 2025-05-02 Makoto Sato

This paper presents null-shot prompting. Null-shot prompting exploits hallucination in large language models (LLMs) by instructing LLMs to utilize information from the "Examples" section that never exists within the provided context to…

Computation and Language · Computer Science 2024-11-19 Pittawat Taveekitworachai , Febri Abdullah , Ruck Thawonmas

As Large Language Models (LLMs) have advanced, they have brought forth new challenges, with one of the prominent issues being LLM hallucination. While various mitigation techniques are emerging to address hallucination, it is equally…

Artificial Intelligence · Computer Science 2023-09-21 Vipula Rawte , Prachi Priya , S. M Towhidul Islam Tonmoy , S M Mehedi Zaman , Amit Sheth , Amitava Das

Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications. However, when deployed in the wild,…

Computation and Language · Computer Science 2023-03-29 Nuno M. Guerreiro , Duarte Alves , Jonas Waldendorf , Barry Haddow , Alexandra Birch , Pierre Colombo , André F. T. Martins

Is automated hallucination detection possible? In this work, we introduce a theoretical framework to analyze the feasibility of automatically detecting hallucinations produced by large language models (LLMs). Inspired by the classical…

Machine Learning · Computer Science 2025-06-03 Amin Karbasi , Omar Montasser , John Sous , Grigoris Velegkas

The widespread adoption of large language models (LLMs) across diverse AI applications is proof of the outstanding achievements obtained in several tasks, such as text mining, text generation, and question answering. However, LLMs are not…

Computation and Language · Computer Science 2023-11-15 Alessandro Bruno , Pier Luigi Mazzeo , Aladine Chetouani , Marouane Tliba , Mohamed Amine Kerkouri