English
Related papers

Related papers: MoRFI: Monotonic Sparse Autoencoder Feature Identi…

200 papers

Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena, but the underlying reasons remain poorly understood. In this paper, we present an empirical analysis and find that, although MLLMs incorrectly generate the…

Computation and Language · Computer Science 2025-02-25 Chenxi Wang , Xiang Chen , Ningyu Zhang , Bozhong Tian , Haoming Xu , Shumin Deng , Huajun Chen

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…

Computation and Language · Computer Science 2024-05-03 Sheng-Chieh Lin , Luyu Gao , Barlas Oguz , Wenhan Xiong , Jimmy Lin , Wen-tau Yih , Xilun Chen

Multimodal Large Language Models (MLLMs) achieve strong performance on tasks like image captioning and visual question answering, but remain prone to hallucinations, where generated text conflicts with the visual input. Prior work links…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Tiancheng Yang , Lin Zhang , Jiaye Lin , Guimin Hu , Di Wang , Lijie Hu

Uncertainty estimation is a necessary component when implementing AI in high-risk settings, such as autonomous cars, medicine, or insurances. Large Language Models (LLMs) have seen a surge in popularity in recent years, but they are subject…

Machine Learning · Computer Science 2024-12-09 Gabriel Y. Arteaga , Thomas B. Schön , Nicolas Pielawski

Large language models (LLMs) often exhibit undesirable behaviors, such as hallucinations and sequence repetitions. We propose to view these behaviors as fallbacks that models exhibit under epistemic uncertainty, and investigate the…

Computation and Language · Computer Science 2025-02-11 Maor Ivgi , Ori Yoran , Jonathan Berant , Mor Geva

Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts…

Machine Learning · Computer Science 2026-02-26 Shiwei Tan , Hengyi Wang , Weiyi Qin , Qi Xu , Zhigang Hua , Hao Wang

We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state, a key factor in countering factual hallucination and ensuring reliable application of LLMs. We observe a robust self-awareness of…

Computation and Language · Computer Science 2024-01-30 Yuxin Liang , Zhuoyang Song , Hao Wang , Jiaxing Zhang

Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses…

Machine Learning · Computer Science 2026-02-03 Prakhar Ganesh , Reza Shokri , Golnoosh Farnadi

Large Language Models (LLMs) are adept at text manipulation -- tasks such as machine translation and text summarization. However, these models can also be prone to hallucination, which can be detrimental to the faithfulness of any answers…

Computation and Language · Computer Science 2024-04-04 Priyesh Vakharia , Devavrat Joshi , Meenal Chavan , Dhananjay Sonawane , Bhrigu Garg , Parsa Mazaheri

Hallucinated facts in large language models (LLMs) have recently been shown to obey a statistical lower bound determined by the monofact rate (related to the classical Good-Turing missing mass estimator) minus model miscalibration (Kalai &…

Computation and Language · Computer Science 2026-03-04 Miranda Muqing Miao , Michael Kearns

Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tuning methods affect…

Computation and Language · Computer Science 2026-02-13 Xu Hu , Yifan Zhang , Songtao Wei , Chen Zhao , Qiannan Li , Bingzhe Li , Feng Chen

Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured text often suffer from 1) reliance on compute-heavy paraphrasing augmentation and 2) the reversal…

Computation and Language · Computer Science 2026-05-07 Xu Pan , Ely Hahami , Jingxuan Fan , Ziqian Xie , Haim Sompolinsky

The finetuning of Large Language Models (LLMs) has significantly advanced their instruction-following capabilities, yet the underlying computational mechanisms driving these improvements remain poorly understood. This study systematically…

Computation and Language · Computer Science 2025-05-28 Junyan Zhang , Yubo Gao , Yibo Yan , Jungang Li , Zhaorui Hou , Sicheng Tao , Shuliang Liu , Song Dai , Yonghua Hei , Junzhuo Li , Xuming Hu

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Machine Learning · Computer Science 2025-08-07 Gonçalo Paulo , Alex Mallen , Caden Juang , Nora Belrose

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Computation and Language · Computer Science 2025-10-20 Jessy Lin , Luke Zettlemoyer , Gargi Ghosh , Wen-Tau Yih , Aram Markosyan , Vincent-Pierre Berges , Barlas Oğuz

Large Language Models (LLMs) are increasingly adopted for complex scientific text generation tasks, yet they often suffer from limitations in accuracy, consistency, and hallucination control. This thesis introduces a Parameter-Efficient…

Computation and Language · Computer Science 2024-11-12 Daniil Sulimov

Large Language Models (LLMs) are known to hallucinate and generate non-factual outputs which can undermine user trust. Traditional methods to directly mitigate hallucinations, such as representation editing and contrastive decoding, often…

Machine Learning · Computer Science 2025-03-11 Prasenjit Dey , Srujana Merugu , Sivaramakrishnan Kaveri

Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal…

Computation and Language · Computer Science 2025-05-29 Qihuang Zhong , Liang Ding , Xiantao Cai , Juhua Liu , Bo Du , Dacheng Tao