English
Related papers

Related papers: Inference-Time Intervention: Eliciting Truthful An…

200 papers

Despite the recent breakthroughs achieved by Large Vision Language Models (LVLMs) in understanding and responding to complex visual-textual contexts, their inherent hallucination tendencies limit their practical application in real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Junzhe Chen , Tianshu Zhang , Shiyu Huang , Yuwei Niu , Linfeng Zhang , Lijie Wen , Xuming Hu

The development of Large Language Models (LLMs) has notably transformed numerous sectors, offering impressive text generation capabilities. Yet, the reliability and truthfulness of these models remain pressing concerns. To this end, we…

Computation and Language · Computer Science 2024-02-12 Satyapriya Krishna , Chirag Agarwal , Himabindu Lakkaraju

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Computation and Language · Computer Science 2025-11-04 Peng Ding , Jun Kuang , Wen Sun , Zongyu Wang , Xuezhi Cao , Xunliang Cai , Jiajun Chen , Shujian Huang

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to…

Computation and Language · Computer Science 2024-08-27 Tianyang Liu , Tianyi Li , Liang Cheng , Mark Steedman

Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across tasks and languages, revolutionizing natural language processing. This paper investigates the naturally emerging representation alignment in LLMs,…

Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task…

Computation and Language · Computer Science 2024-06-07 Guijin Son , Sangwon Baek , Sangdae Nam , Ilgyun Jeong , Seungone Kim

Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Modelling (IM), which trains LMs by applying a loss function to…

Computation and Language · Computer Science 2024-10-04 Zhengyan Shi , Adam X. Yang , Bin Wu , Laurence Aitchison , Emine Yilmaz , Aldo Lipani

Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish instructions from data content make them vulnerable to…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuexin Li , Yue Liu , Yangqiu Song , Bryan Hooi

Large Language Models (LLMs) can generate factually inaccurate content even if they have corresponding knowledge, which critically undermines their reliability. Existing approaches attempt to mitigate this by incorporating uncertainty in QA…

Computation and Language · Computer Science 2026-04-14 Xiaoning Dong , Chengyan Wu , Yajie Wen , Yu Chen , Yun Xue , Jing Zhang , Wei Xu , Bolei Ma

Motivational interviewing (MI) promotes behavioural change in substance use disorders. Its fidelity is measured using the Motivational Interviewing Treatment Integrity (MITI) framework. While large language models (LLMs) can potentially…

Computation and Language · Computer Science 2026-03-05 Aishwariya Jha , Prakrithi Shivaprakash , Lekhansh Shukla , Animesh Mukherjee , Prabhat Chand , Pratima Murthy

Multimodal Large Language Models (MLLMs) excel in numerous vision-language tasks yet suffer from hallucinations, producing content inconsistent with input visuals, that undermine reliability in precision-sensitive domains. This issue stems…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Nan Sun , Zhenyu Zhang , Xixun Lin , Kun Wang , Yanmin Shang , Naibin Gu , Shuohuan Wang , Yu Sun , Hua Wu , Haifeng Wang , Yanan Cao

Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be…

Machine Learning · Statistics 2026-02-03 Shokichi Takakura , Akifumi Wachi , Rei Higuchi , Kohei Miyaguchi , Taiji Suzuki

Although Large Language Models (LLMs) have demonstrated extraordinary capabilities in many domains, they still have a tendency to hallucinate and generate fictitious responses to user requests. This problem can be alleviated by augmenting…

Information Retrieval · Computer Science 2023-06-09 Jiongnan Liu , Jiajie Jin , Zihan Wang , Jiehan Cheng , Zhicheng Dou , Ji-Rong Wen

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Computation and Language · Computer Science 2024-03-12 Yue Zhang , Leyang Cui , Wei Bi , Shuming Shi

Truthfulness (adherence to factual accuracy) and utility (satisfying human needs and instructions) are both fundamental aspects of Large Language Models, yet these goals often conflict (e.g., sell a car with known flaws), which makes it…

Artificial Intelligence · Computer Science 2025-04-29 Zhe Su , Xuhui Zhou , Sanketh Rangreji , Anubha Kabra , Julia Mendelsohn , Faeze Brahman , Maarten Sap

Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Kejia Chen , Jiawen Zhang , Jiacong Hu , Kewei Gao , Jian Lou , Zunlei Feng , Mingli Song

Inference-time steering aims to alter a large language model's (LLM's) responses without changing its parameters, but a central challenge is identifying the internal modules that most strongly govern the target behavior. Existing approaches…

Computation and Language · Computer Science 2025-10-02 Li-Ming Zhan , Bo Liu , Chengqiang Xie , Jiannong Cao , Xiao-Ming Wu

Large language models (LLMs) have achieved a degree of success in generating coherent and contextually relevant text, yet they remain prone to a significant challenge known as hallucination: producing information that is not substantiated…

Computation and Language · Computer Science 2024-10-28 Ray Li , Tanishka Bagade , Kevin Martinez , Flora Yasmin , Grant Ayala , Michael Lam , Kevin Zhu

Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…

Cryptography and Security · Computer Science 2026-04-24 Naheed Rayhan , Sohely Jahan

Intent, a critical cognitive notion and mental state, is ubiquitous in human communication and problem-solving. Accurately understanding the underlying intent behind questions is imperative to reasoning towards correct answers. However,…

Computation and Language · Computer Science 2026-04-17 Yuwei Yin , Giuseppe Carenini