English
Related papers

Related papers: Locating and Editing Factual Associations in GPT

200 papers

Low-Rank Adaptation (LoRA) is a popular technique for efficient fine-tuning of foundation models. However, applying LoRA in federated learning environments, where data is distributed across multiple clients, presents unique challenges.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-01 Raghav Singhal , Kaustubh Ponkshe , Praneeth Vepakomma

When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less is…

Computation and Language · Computer Science 2026-03-17 Javier Marín

Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they are actually rewarding. In this paper we develop…

Computation and Language · Computer Science 2025-05-21 David Reber , Sean Richardson , Todd Nief , Cristina Garbacea , Victor Veitch

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, yet they remain constrained by the finite capacity of their context windows and the inherent difficulty of maintaining long-term…

Computation and Language · Computer Science 2026-02-03 Xun Xu

Large-scale pretrained language models are surprisingly good at recalling factual knowledge presented in the training corpus. In this paper, we present preliminary studies on how factual knowledge is stored in pretrained Transformers by…

Computation and Language · Computer Science 2022-03-11 Damai Dai , Li Dong , Yaru Hao , Zhifang Sui , Baobao Chang , Furu Wei

Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training (Meng et al., 2023). However, these editing methods have only been evaluated on statements about encyclopedic…

Computation and Language · Computer Science 2023-10-27 Anshita Gupta , Debanjan Mondal , Akshay Krishna Sheshadri , Wenlong Zhao , Xiang Lorraine Li , Sarah Wiegreffe , Niket Tandon

Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address this, we propose FABLE, a hierarchical framework that…

Computation and Language · Computer Science 2026-04-15 Peng Wang , Biyu Zhou , Xuehai Tang , Jizhong Han , Songlin Hu

Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…

Computation and Language · Computer Science 2025-10-27 Fufang Wen , Shichang Zhang

Despite the continuous research and evolution of language models, they sometimes underperform previous versions. Existing approaches to overcome these challenges are resource-intensive, highlighting the need for alternatives that enable…

Computation and Language · Computer Science 2026-02-19 Namkyung Yoon , Kyeonghyun Yoo , Wooyong Jung , Sanghong Kim , Hwangnam Kim

Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest…

Machine Learning · Computer Science 2024-11-26 Christopher M. Ackerman

Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically rely on memorizing isolated artifacts and struggle with imperceptible manipulation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Jun Zhou , Bingwen Hu , Yaxiong Wang , Zhedong Zheng , Yongzhen Wang , Yuchen Zhang , Ping Liu

We study estimation and inference using data collected by reinforcement learning (RL) algorithms. These algorithms adaptively experiment by interacting with individual units over multiple stages, updating their strategies based on past…

Machine Learning · Statistics 2025-10-06 Vasilis Syrgkanis , Ruohan Zhan

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to…

Computation and Language · Computer Science 2024-04-18 Mert Yuksekgonul , Varun Chandrasekaran , Erik Jones , Suriya Gunasekar , Ranjita Naik , Hamid Palangi , Ece Kamar , Besmira Nushi

Transformer-based language models (LMs) are at the core of modern NLP, but their internal prediction construction process is opaque and largely not understood. In this work, we make a substantial step towards unveiling this underlying…

Computation and Language · Computer Science 2022-10-14 Mor Geva , Avi Caciularu , Kevin Ro Wang , Yoav Goldberg

State-of-the-art machine translation models are still not on par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. However, not all…

Computation and Language · Computer Science 2019-08-14 Rongxiang Weng , Hao Zhou , Shujian Huang , Lei Li , Yifan Xia , Jiajun Chen

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Computation and Language · Computer Science 2024-06-18 Belinda Z. Li , Emmy Liu , Alexis Ross , Abbas Zeitoun , Graham Neubig , Jacob Andreas

Multilingual knowledge editing (MKE) aims to simultaneously update factual knowledge across multiple languages within large language models (LLMs). Previous research indicates that the same knowledge across different languages within LLMs…

Computation and Language · Computer Science 2024-12-18 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Verifying the correctness of a textual statement requires not only semantic reasoning about the meaning of words, but also symbolic reasoning about logical operations like count, superlative, aggregation, etc. In this work, we propose…

Computation and Language · Computer Science 2020-04-29 Wanjun Zhong , Duyu Tang , Zhangyin Feng , Nan Duan , Ming Zhou , Ming Gong , Linjun Shou , Daxin Jiang , Jiahai Wang , Jian Yin

Generative relation extraction (RE) commonly involves first reformulating RE as a linguistic modeling problem easily tackled with pre-trained language models (PLM) and then fine-tuning a PLM with supervised cross-entropy loss. Although…

Computation and Language · Computer Science 2025-01-07 Jiaxin Duan , Fengyu Lu , Junfei Liu

The success of Transformer-based Language Models (LMs) stems from their attention mechanism. While this mechanism has been extensively studied in explainability research, particularly through the attention values obtained during the forward…

Computation and Language · Computer Science 2024-12-24 Shahar Katz , Lior Wolf
‹ Prev 1 3 4 5 6 7 10 Next ›