English
Related papers

Related papers: Learning and Unlearning of Fabricated Knowledge in…

200 papers

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

Computation and Language · Computer Science 2025-02-13 Çağatay Yıldız , Nishaanth Kanna Ravichandran , Nitin Sharma , Matthias Bethge , Beyza Ermis

We evaluate LLMs' language understanding capacities on simple inference tasks that most humans find trivial. Specifically, we target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii)…

Computation and Language · Computer Science 2024-04-12 Victoria Basmov , Yoav Goldberg , Reut Tsarfaty

Factual knowledge extraction aims to explicitly extract knowledge parameterized in pre-trained language models for application in downstream tasks. While prior work has been investigating the impact of supervised fine-tuning data on the…

Computation and Language · Computer Science 2025-05-30 Xuan Gong , Hanbo Huang , Shiyu Liang

Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating…

Computation and Language · Computer Science 2024-12-17 Fali Wang , Runxue Bao , Suhang Wang , Wenchao Yu , Yanchi Liu , Wei Cheng , Haifeng Chen

Large language models (LLMs) have shown incredible performance in completing various real-world tasks. The current paradigm of knowledge learning for LLMs is mainly based on learning from examples, in which LLMs learn the internal rule…

Computation and Language · Computer Science 2024-12-17 Wenkai Yang , Yankai Lin , Jie Zhou , Ji-Rong Wen

Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this…

Computation and Language · Computer Science 2026-04-08 Alexandros Christoforos

Question answering models can use rich knowledge sources -- up to one hundred retrieved passages and parametric knowledge in the large-scale language model (LM). Prior work assumes information in such knowledge sources is consistent with…

Computation and Language · Computer Science 2022-10-26 Hung-Ting Chen , Michael J. Q. Zhang , Eunsol Choi

Large language models (LLMs) are widely used in decision-making, but their reliability, especially in critical tasks like healthcare, is not well-established. Therefore, understanding how LLMs reason and make decisions is crucial for their…

Machine Learning · Computer Science 2025-02-25 Ze Yu Zhang , Arun Verma , Finale Doshi-Velez , Bryan Kian Hsiang Low

This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in,…

Computation and Language · Computer Science 2025-09-04 Taiming Lu , Philipp Koehn

Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training…

Computation and Language · Computer Science 2026-05-26 Hippolyte Pilchen , Romain Fabre , Franck Signe Talla , Patrick Perez , Edouard Grave

Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work…

Computation and Language · Computer Science 2024-03-21 Adam Tauman Kalai , Santosh S. Vempala

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase…

Computation and Language · Computer Science 2024-10-08 Bozhong Tian , Xiaozhuan Liang , Siyuan Cheng , Qingbin Liu , Mengru Wang , Dianbo Sui , Xi Chen , Huajun Chen , Ningyu Zhang

Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data. In order to cleanly measure and…

Computation and Language · Computer Science 2024-07-30 Till Speicher , Mohammad Aflah Khan , Qinyuan Wu , Vedant Nanda , Soumi Das , Bishwamittra Ghosh , Krishna P. Gummadi , Evimaria Terzi

Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge. These limitations contrast with the human ability to continuously learn from new experiences and acquire knowledge throughout…

Computation and Language · Computer Science 2025-05-01 Xu Pan , Ely Hahami , Zechen Zhang , Haim Sompolinsky

Natural-language prompts have recently been used to coax pretrained language models into performing other AI tasks, using a fill-in-the-blank paradigm (Petroni et al., 2019) or a few-shot extrapolation paradigm (Brown et al., 2020). For…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Jason Eisner

Large language models (LLMs) encode vast amounts of pre-trained knowledge in their parameters, but updating them as real-world information evolves remains a challenge. Existing methodologies and benchmarks primarily target entity…

Computation and Language · Computer Science 2025-04-18 Aochong Oliver Li , Tanya Goyal

Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "when" LLMs hallucinate, our work explains "why" and directly…

Computation and Language · Computer Science 2025-07-15 Yuan He , Bailan He , Zifeng Ding , Alisia Lupidi , Yuqicheng Zhu , Shuo Chen , Caiqi Zhang , Jiaoyan Chen , Yunpu Ma , Volker Tresp , Ian Horrocks

Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satisfactory performance in downstream tasks. As large language…

Computation and Language · Computer Science 2025-01-07 Yun Luo , Zhen Yang , Fandong Meng , Yafu Li , Jie Zhou , Yue Zhang

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this article, we probe BERT specifically to understand and measure the relational…

Computation and Language · Computer Science 2021-09-09 Jonas Wallat , Jaspreet Singh , Avishek Anand

The remarkable performance of Multimodal Large Language Models (MLLMs) has unequivocally demonstrated their proficient understanding capabilities in handling a wide array of visual tasks. Nevertheless, the opaque nature of their black-box…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Minghe Gao , Shuang Chen , Liang Pang , Yuan Yao , Jisheng Dang , Wenqiao Zhang , Juncheng Li , Siliang Tang , Yueting Zhuang , Tat-Seng Chua