中文
相关论文

相关论文: Different types of syntactic agreement recruit the…

200 篇论文

Large Language Models (LLMs) exhibit a robust mastery of syntax when processing and generating text. While this suggests internalized understanding of hierarchical syntax and dependency relations, the precise mechanism by which they…

计算与语言 · 计算机科学 2025-11-11 Ananth Agarwal , Jasper Jian , Christopher D. Manning , Shikhar Murty

Learning representations that accurately model semantics is an important goal of natural language processing research. Many semantic phenomena depend on syntactic structure. Recent work examines the extent to which state-of-the-art models…

计算与语言 · 计算机科学 2019-08-28 Geoff Bacon , Terry Regier

In this paper, our goal is to investigate to what degree multilingual pretrained language models capture cross-linguistically valid abstract linguistic representations. We take the approach of developing curated synthetic data on a large…

计算与语言 · 计算机科学 2024-12-02 Vivi Nastase , Chunyang Jiang , Giuseppe Samo , Paola Merlo

Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe…

计算与语言 · 计算机科学 2025-08-26 Qiwei Peng , Yekun Chai , Anders Søgaard

Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and analyses of multilingual models have employed correlational…

计算与语言 · 计算机科学 2022-10-27 Aaron Mueller , Yu Xia , Tal Linzen

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

计算与语言 · 计算机科学 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal organization remains elusive. In this work, we investigate…

计算与语言 · 计算机科学 2026-04-22 Aastha A K Verma , Anwoy Chatterjee , Mehak Gupta , Tanmoy Chakraborty

We employ new tools from mechanistic interpretability in order to ask whether the internal structure of large language models (LLMs) shows correspondence to the linguistic structures which underlie the languages on which they are trained.…

计算与语言 · 计算机科学 2024-10-15 Ruochen Zhang , Qinan Yu , Matianyu Zang , Carsten Eickhoff , Ellie Pavlick

LSTMs trained on next-word prediction can accurately perform linguistic tasks that require tracking long-distance syntactic dependencies. Notably, model accuracy approaches human performance on number agreement tasks (Gulordava et al.,…

计算与语言 · 计算机科学 2022-11-02 Priyanka Sukumaran , Conor Houghton , Nina Kazanina

Large Language Models (LLMs) can be deployed in situations where they process positive/negative interactions with other agents. We study how this is done under the sociological framework of social balance, which explains the emergence of…

计算与语言 · 计算机科学 2026-01-07 Pedro Cisneros-Velarde

The emergent few-shot reasoning capabilities of Large Language Models (LLMs) have excited the natural language and machine learning community over recent years. Despite of numerous successful applications, the underlying mechanism of such…

计算与语言 · 计算机科学 2023-06-09 Xiaojuan Tang , Zilong Zheng , Jiaqi Li , Fanxu Meng , Song-Chun Zhu , Yitao Liang , Muhan Zhang

We deploy the methods of controlled psycholinguistic experimentation to shed light on the extent to which the behavior of neural network language models reflects incremental representations of syntactic state. To do so, we examine model…

计算与语言 · 计算机科学 2019-03-11 Richard Futrell , Ethan Wilcox , Takashi Morita , Peng Qian , Miguel Ballesteros , Roger Levy

Analogical reasoning -- the capacity to identify and map structural relationships between different domains -- is fundamental to human cognition and learning. Recent studies have shown that large language models (LLMs) can sometimes match…

计算与语言 · 计算机科学 2025-11-21 Sam Musker , Alex Duchnowski , Raphaël Millière , Ellie Pavlick

Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks. However, recent research has highlighted their sensitivity to variations in input prompts. To deploy LLMs in a safe and reliable…

计算与语言 · 计算机科学 2025-04-30 Harsh Raj , Vipul Gupta , Domenic Rosati , Subhabrata Majumdar

Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM families (12…

计算与语言 · 计算机科学 2025-05-21 Ruchira Dhar , Anders Søgaard

Large Language Models (LLMs) are commonly criticized for not understanding language. However, many critiques focus on cognitive abilities that, in humans, are distinct from language processing. Here, we instead study a kind of understanding…

计算与语言 · 计算机科学 2025-04-29 Joseph M. Denning , Xiaohan Hannah Guo , Bryor Snefjella , Idan A. Blank

We introduce a novel analysis that leverages linguistic minimal pairs to probe the internal linguistic representations of Large Language Models (LLMs). By measuring the similarity between LLM activation differences across minimal pairs, we…

计算与语言 · 计算机科学 2024-12-16 Xinyu Zhou , Delong Chen , Samuel Cahyawijaya , Xufeng Duan , Zhenguang G. Cai

Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent…

计算与语言 · 计算机科学 2022-04-20 Shunsuke Kando , Hiroshi Noji , Yusuke Miyao

Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowledge recall; however, it has only focused on English…

计算与语言 · 计算机科学 2025-06-12 Constanza Fierro , Negar Foroutan , Desmond Elliott , Anders Søgaard

Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…

软件工程 · 计算机科学 2026-04-07 Rabia Iftikhar , Andreas Rausch