English
Related papers

Related papers: Entity Tracking in Language Models

200 papers

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

Computation and Language · Computer Science 2023-11-07 Zhenhong Zhou , Jiuyang Xiang , Chaomeng Chen , Sen Su

Entity matching (EM) is a critical task in data integration, aiming to identify records across different datasets that refer to the same real-world entities. Traditional methods often rely on manually engineered features and rule-based…

Computation and Language · Computer Science 2024-06-03 Qianyu Huang , Tongfang Zhao

This work introduces approaches to assessing phrase breaks in ESL learners' speech using pre-trained language models (PLMs) and large language models (LLMs). There are two tasks: overall assessment of phrase break for a speech clip and…

Computation and Language · Computer Science 2023-06-09 Zhiyi Wang , Shaoguang Mao , Wenshan Wu , Yan Xia , Yan Deng , Jonathan Tien

Are Large language models (LLMs) temporally grounded? Since LLMs cannot perceive and interact with the environment, it is impossible to answer this question directly. Instead, we provide LLMs with textual narratives and probe them with…

Computation and Language · Computer Science 2023-11-17 Yifu Qiu , Zheng Zhao , Yftah Ziser , Anna Korhonen , Edoardo M. Ponti , Shay B. Cohen

Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited from such knowledge transfer because of its distinct…

Computation and Language · Computer Science 2023-02-14 Janvijay Singh , Fan Bai , Zhen Wang

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

Large Language Models (LLMs) exhibit emergent capabilities in structured domains, suggesting they may implicitly internalize high-fidelity representations of world models. While probing techniques have shown promising signs of this in…

Artificial Intelligence · Computer Science 2025-08-28 Romain Harang , Jason Naradowsky , Yaswitha Gujju , Yusuke Miyao

Pre-trained large language models (LLMs) capture procedural knowledge about the world. Recent work has leveraged LLM's ability to generate abstract plans to simplify challenging control tasks, either by action scoring, or action modeling…

Computation and Language · Computer Science 2023-05-09 Yue Wu , So Yeon Min , Yonatan Bisk , Ruslan Salakhutdinov , Amos Azaria , Yuanzhi Li , Tom Mitchell , Shrimai Prabhumoye

Recent work exploring the capabilities of pre-trained large language models (LLMs) has demonstrated their ability to act as general pattern machines by completing complex token sequences representing a wide array of tasks, including…

Computers and Society · Computer Science 2024-03-25 Seyed Parsa Neshaei , Richard Lee Davis , Adam Hazimeh , Bojan Lazarevski , Pierre Dillenbourg , Tanja Käser

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can…

Computation and Language · Computer Science 2022-01-24 Vinsen Marselino Andreas , Genta Indra Winata , Ayu Purwarianti

Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes. Prior work has studied targeted updates to LMs, injecting individual…

Computation and Language · Computer Science 2023-05-03 Yasumasa Onoe , Michael J. Q. Zhang , Shankar Padmanabhan , Greg Durrett , Eunsol Choi

Code generation and understanding are critical capabilities for large language models (LLMs). Thus, most LLMs are pretrained and fine-tuned on code data. However, these datasets typically treat code as static strings and rarely exploit the…

This study introduces a novel approach for analyzing and modifying entity relationships in GPT models, diverging from ROME's entity-focused methods. We develop a relation tracing technique to understand the influence of language model…

Computation and Language · Computer Science 2024-01-09 Jiahang Li , Taoyu Chen , Yuanli Wang

Dialogue State Tracking (DST) is critical for comprehensively interpreting user and system utterances, thereby forming the cornerstone of efficient dialogue systems. Despite past research efforts focused on enhancing DST performance through…

Computation and Language · Computer Science 2023-07-25 Yukyung Lee , Takyoung Kim , Hoonsang Yoon , Pilsung Kang , Junseong Bang , Misuk Kim

We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two…

Computation and Language · Computer Science 2025-07-22 Masaki Sakata , Benjamin Heinzerling , Sho Yokoi , Takumi Ito , Kentaro Inui

Understanding longer narratives or participating in conversations requires tracking of discourse entities that have been mentioned. Indefinite noun phrases (NPs), such as 'a dog', frequently introduce discourse entities but this behavior is…

Computation and Language · Computer Science 2022-05-10 Sebastian Schuster , Tal Linzen

Humans use language to refer to entities in the external world. Motivated by this, in recent years several models that incorporate a bias towards learning entity representations have been proposed. Such entity-centric models have shown…

Computation and Language · Computer Science 2019-05-17 Laura Aina , Carina Silberer , Matthijs Westera , Ionut-Teodor Sorodoc , Gemma Boleda

Instructions-tuned Large Language Models (LLMs) gained recently huge popularity thanks to their ability to interact with users through conversation. In this work we aim to evaluate their ability to complete multi-turn tasks and interact…

Computation and Language · Computer Science 2023-08-04 Vojtěch Hudeček , Ondřej Dušek

Pre-trained language models (PLMs) cannot well recall rich factual knowledge of entities exhibited in large-scale corpora, especially those rare entities. In this paper, we propose to build a simple but effective Pluggable Entity Lookup…

Computation and Language · Computer Science 2022-05-18 Deming Ye , Yankai Lin , Peng Li , Maosong Sun , Zhiyuan Liu

Work done to uncover the knowledge encoded within pre-trained language models rely on annotated corpora or human-in-the-loop methods. However, these approaches are limited in terms of scalability and the scope of interpretation. We propose…

Computation and Language · Computer Science 2023-10-23 Basel Mousi , Nadir Durrani , Fahim Dalvi