English
Related papers

Related papers: Testing the Limits of Truth Directions in LLMs

200 papers

Large Language Models (LLMs) have been transformative. They are pre-trained foundational models that are self-supervised and can be adapted with fine tuning to a wide range of natural language tasks, each of which previously would have…

Computation and Language · Computer Science 2023-02-22 Terrence Sejnowski

This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal…

Computation and Language · Computer Science 2025-10-13 Tao Feng , Lizhen Qu , Niket Tandon , Zhuang Li , Xiaoxi Kang , Gholamreza Haffari

Large Language Models (LLMs) are conversational interfaces. As such, LLMs have the potential to assist their users not only when they can fully specify the task at hand, but also to help them define, explore, and refine what they need…

Computation and Language · Computer Science 2025-05-12 Philippe Laban , Hiroaki Hayashi , Yingbo Zhou , Jennifer Neville

Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with…

Artificial Intelligence · Computer Science 2025-06-03 Zhuojun Gu , Quan Wang , Shuchu Han

Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer…

Computation and Language · Computer Science 2024-02-16 Olivia Macmillan-Scott , Mirco Musolesi

We investigate the abilities of 28 Large language Models (LLMs) to reason about cardinal directions (CDs) using a benchmark generated from a set of templates, extensively testing an LLM's ability to determine the correct CD given a…

Computation and Language · Computer Science 2025-11-11 Anthony G Cohn , Robert E Blackwell

The scaling of large language models (LLMs) emphasizes increasing depth, yet performance gains diminish with added layers. Prior work introduces the concept of "effective depth", arguing that deeper models fail to fully utilize their layers…

Computation and Language · Computer Science 2025-12-17 Yi Hu , Cai Zhou , Muhan Zhang

With the development of large language models (LLMs) like the GPT series, their widespread use across various application scenarios presents a myriad of challenges. This review initially explores the issue of domain specificity, where LLMs…

Computation and Language · Computer Science 2023-10-23 Xiaoliang Chen , Liangbin Li , Le Chang , Yunhe Huang , Yuxuan Zhao , Yuxiao Zhang , Dinuo Li

Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance loss. However, such claims are typically drawn from narrow…

Artificial Intelligence · Computer Science 2026-01-28 Xinyuan Song , Keyu Wang , PengXiang Li , Lu Yin , Shiwei Liu

In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To…

Computation and Language · Computer Science 2024-02-14 Ryan Liu , Theodore R. Sumers , Ishita Dasgupta , Thomas L. Griffiths

Recent advances in large language models (LLMs) have sparked growing interest in integrating language-driven techniques into trajectory prediction. By leveraging their semantic and reasoning capabilities, LLMs are reshaping how autonomous…

Computation and Language · Computer Science 2025-10-08 Yi Xu , Ruining Yang , Yitian Zhang , Jianglin Lu , Mingyuan Zhang , Yizhou Wang , Lili Su , Yun Fu

Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanations can lead to unsupported confidence in LLMs, thus…

Computation and Language · Computer Science 2024-05-20 Andreas Madsen , Sarath Chandar , Siva Reddy

Direction reasoning is essential for intelligent systems to understand the real world. While existing work focuses primarily on spatial reasoning, compass direction reasoning remains underexplored. To address this, we propose the Compass…

Artificial Intelligence · Computer Science 2024-12-24 Hang Yin , Zhifeng Lin , Xin Liu , Bin Sun , Kan Li

The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world.…

Machine Learning · Computer Science 2024-03-05 Wes Gurnee , Max Tegmark

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

Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. Yet, their ability to provide well-grounded rationalizations for knowledge-intensive tasks remains under-explored. Such tasks,…

Computation and Language · Computer Science 2024-02-02 Aditi Mishra , Sajjadur Rahman , Hannah Kim , Kushan Mitra , Estevam Hruschka

Do LLMs genuinely incorporate external definitions, or do they primarily rely on their parametric knowledge? To address these questions, we conduct controlled experiments across multiple explanation benchmark datasets (general and…

Computation and Language · Computer Science 2026-02-26 Seyedali Mohammadi , Bhaskara Hanuma Vedula , Hemank Lamba , Edward Raff , Ponnurangam Kumaraguru , Francis Ferraro , Manas Gaur

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

Computation and Language · Computer Science 2025-01-30 Yuxuan Li , Hirokazu Shirado , Sauvik Das

Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-turn setting. However, belief can change…

Computation and Language · Computer Science 2024-06-03 Rongwu Xu , Brian S. Lin , Shujian Yang , Tianqi Zhang , Weiyan Shi , Tianwei Zhang , Zhixuan Fang , Wei Xu , Han Qiu