中文
相关论文

相关论文: The Model Agreed, But Didn't Learn: Diagnosing Sur…

200 篇论文

Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit…

机器学习 · 计算机科学 2024-12-03 Eduardo Slonski

Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-modifying ME and parameter-preserving ME (integrating extra…

计算与语言 · 计算机科学 2024-02-20 Zihao Lin , Mohammad Beigi , Hongxuan Li , Yufan Zhou , Yuxiang Zhang , Qifan Wang , Wenpeng Yin , Lifu Huang

Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure belief depth and use it to evaluate the success of knowledge…

计算与语言 · 计算机科学 2025-10-22 Stewart Slocum , Julian Minder , Clément Dumas , Henry Sleight , Ryan Greenblatt , Samuel Marks , Rowan Wang

Large language models (LLMs) demonstrate remarkable breadth of knowledge, yet their ability to reason about computational processes remains poorly understood. Closing this gap matters for practitioners who rely on LLMs to guide algorithm…

计算与语言 · 计算机科学 2026-04-07 Sohan Venkatesh , Ashish Mahendran Kurapath , Tejas Melkote

Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks. Current research focuses on enhancing their performance within their existing knowledge. Despite their…

计算与语言 · 计算机科学 2023-05-31 Zhangyue Yin , Qiushi Sun , Qipeng Guo , Jiawen Wu , Xipeng Qiu , Xuanjing Huang

Large language models (LLMs) draw on both contextual information and parametric memory, yet these sources can conflict. Prior studies have largely examined this issue in contextual question answering, implicitly assuming that tasks should…

计算与语言 · 计算机科学 2026-04-21 Kaiser Sun , Fan Bai , Mark Dredze

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

机器学习 · 计算机科学 2025-10-27 Jerry Huang , Peng Lu , Qiuhao Zeng

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…

Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of the physical world. Consequently, while these agents…

计算与语言 · 计算机科学 2026-01-21 Baochang Ren , Yunzhi Yao , Rui Sun , Shuofei Qiao , Ningyu Zhang , Huajun Chen

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the…

计算与语言 · 计算机科学 2025-03-04 Tianci Liu , Ruirui Li , Yunzhe Qi , Hui Liu , Xianfeng Tang , Tianqi Zheng , Qingyu Yin , Monica Xiao Cheng , Jun Huan , Haoyu Wang , Jing Gao

Large language models (LLMs) often require vast amounts of text to effectively acquire new knowledge. While continuing pre-training on large corpora or employing retrieval-augmented generation (RAG) has proven successful, updating an LLM…

计算与语言 · 计算机科学 2025-08-11 Hugo Abonizio , Thales Almeida , Roberto Lotufo , Rodrigo Nogueira

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

计算与语言 · 计算机科学 2024-12-06 Sourav Banerjee , Ayushi Agarwal , Eishkaran Singh

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit…

计算与语言 · 计算机科学 2025-02-11 Aliakbar Nafar , Kristen Brent Venable , Parisa Kordjamshidi

In recent years, large language models (LLMs), such as GPTs, have attained great impact worldwide. However, how to adapt these LLMs to better suit the vertical domain-specific tasks by utilizing external knowledge remains not completely…

计算与语言 · 计算机科学 2023-11-03 Peng Fu , Yiming Zhang , Haobo Wang , Weikang Qiu , Junbo Zhao

Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for information or task-solving skills becoming outdated, as their knowledge, stored directly within…

计算与语言 · 计算机科学 2024-04-16 Jerry Huang , Prasanna Parthasarathi , Mehdi Rezagholizadeh , Sarath Chandar

Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing model editing methods can address this challenge, they…

机器学习 · 计算机科学 2025-08-07 Xin Liu , Qiyang Song , Shaowen Xu , Kerou Zhou , Wenbo Jiang , Xiaoqi Jia , Weijuan Zhang , Heqing Huang , Yakai Li

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and…

机器学习 · 计算机科学 2025-05-27 Zexi Li , Xiangzhu Wang , William F. Shen , Meghdad Kurmanji , Xinchi Qiu , Dongqi Cai , Chao Wu , Nicholas D. Lane

Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a capability known as in-context learning (ICL). Prior work on synthetic tasks has shown that…

计算与语言 · 计算机科学 2026-05-29 Hua-Dong Xiong , Li Ji-An , Robert C. Wilson , Kwonjoon Lee , Xue-Xin Wei

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new…

计算与语言 · 计算机科学 2026-05-08 Hanxiang Chao , Yihan Bai , Rui Sheng , Tianle Li , Yushi Sun

One of the major aspects contributing to the striking performance of large language models (LLMs) is the vast amount of factual knowledge accumulated during pre-training. Yet, many LLMs suffer from self-inconsistency, which raises doubts…

计算与语言 · 计算机科学 2024-10-07 Anastasiia Sedova , Robert Litschko , Diego Frassinelli , Benjamin Roth , Barbara Plank