English
Related papers

Related papers: Where Knowledge Collides: A Mechanistic Study of I…

200 papers

Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. However, the specific manifestations of…

Computation and Language · Computer Science 2026-04-20 Renfei Dang , Peng Hu , Zhejian Lai , Changjiang Gao , Min Zhang , Shujian Huang

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e., be crosslingual? This study evaluates state-of-the-art…

Computation and Language · Computer Science 2025-03-05 Lynn Chua , Badih Ghazi , Yangsibo Huang , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Amer Sinha , Chulin Xie , Chiyuan Zhang

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized…

Artificial Intelligence · Computer Science 2025-03-13 Jian Gao , Xiao Zhang , Ji Wu , Miao Li

Currently, contextualized word representations are learned by intricate neural network models, such as masked neural language models (MNLMs). The new representations significantly enhanced the performance in automated question answering by…

Computation and Language · Computer Science 2019-11-11 Sunjae Kwon , Cheongwoong Kang , Jiyeon Han , Jaesik Choi

This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions. Specifically, we focus on addressing known-unknown questions, characterized by high…

Computation and Language · Computer Science 2024-07-03 Alfonso Amayuelas , Kyle Wong , Liangming Pan , Wenhu Chen , William Wang

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while…

Computation and Language · Computer Science 2024-10-08 Taiming Lu , Muhan Gao , Kuai Yu , Adam Byerly , Daniel Khashabi

Domain-specific instruction-tuning has become the defacto standard for improving the performance of large language models (LLMs) in specialized applications, e.g., medical question answering. Since the instruction-tuning dataset might…

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

Large language models learn and continually learn through the accumulation of gradient-based updates, but how individual pieces of new information affect existing knowledge, leading to both beneficial generalization and problematic…

Computation and Language · Computer Science 2025-04-15 Chen Sun , Renat Aksitov , Andrey Zhmoginov , Nolan Andrew Miller , Max Vladymyrov , Ulrich Rueckert , Been Kim , Mark Sandler

Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only the task's goal without specific details about potential issues in the…

Computation and Language · Computer Science 2024-11-11 Guangliang Liu , Haitao Mao , Bochuan Cao , Zhiyu Xue , Xitong Zhang , Rongrong Wang , Jiliang Tang , Kristen Johnson

Underlying mechanisms of memorization in LLMs -- the verbatim reproduction of training data -- remain poorly understood. What exact part of the network decides to retrieve a token that we would consider as start of memorization sequence?…

Computation and Language · Computer Science 2026-02-04 Ilya Lasy , Peter Knees , Stefan Woltran

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

Computation and Language · Computer Science 2026-03-18 Tianyi Zhou , Johanne Medina , Sanjay Chawla

Large language models (LLMs) can perform remarkably complex tasks, yet the fine-grained details of how these capabilities emerge during pretraining remain poorly understood. Scaling laws on validation loss tell us how much a model improves…

Computation and Language · Computer Science 2026-04-10 Emmy Liu , Kaiser Sun , Millicent Li , Isabelle Lee , Lindia Tjuatja , Jen-tse Huang , Graham Neubig

In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation. These effects are formulated as non-linear…

Machine Learning · Computer Science 2024-05-21 Siyu Lou , Yuntian Chen , Xiaodan Liang , Liang Lin , Quanshi Zhang

Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. Drawing an analogy to the human psyche's conflict between evolutionary survival…

Computation and Language · Computer Science 2023-11-16 Zi Yin , Wei Ding , Jia Liu

Recent advancements in large language models (LLMs) have enhanced natural-language reasoning. However, their limited parametric memory and susceptibility to hallucination present persistent challenges for tasks requiring accurate,…

Computation and Language · Computer Science 2025-06-02 Yu-Hsuan Lin , Qian-Hui Chen , Yi-Jie Cheng , Jia-Ren Zhang , Yi-Hung Liu , Liang-Yu Hsia , Yun-Nung Chen

Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate…

Computation and Language · Computer Science 2024-10-16 Deniz Bayazit , Negar Foroutan , Zeming Chen , Gail Weiss , Antoine Bosselut

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…

Computation and Language · Computer Science 2024-09-24 Diego Calanzone , Stefano Teso , Antonio Vergari

Large language models (LLMs) can learn from a few demonstrations provided at inference time. We study this in-context learning phenomenon through the lens of Gaussian Processes (GPs). We build controlled experiments where models observe…

Machine Learning · Computer Science 2026-02-13 Elif Akata , Konstantinos Voudouris , Vincent Fortuin , Eric Schulz

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

Computation and Language · Computer Science 2024-10-10 Bozhou Li , Hao Liang , Yang Li , Fangcheng Fu , Hongzhi Yin , Conghui He , Wentao Zhang
‹ Prev 1 8 9 10 Next ›