English
Related papers

Related papers: Eliciting Latent Knowledge from Quirky Language Mo…

200 papers

Explaining the black-box predictions of NLP models naturally and accurately is an important open problem in natural language generation. These free-text explanations are expected to contain sufficient and carefully-selected evidence to form…

Computation and Language · Computer Science 2023-07-12 Qintong Li , Zhiyong Wu , Lingpeng Kong , Wei Bi

Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these…

Computation and Language · Computer Science 2023-12-08 Kevin Liu , Stephen Casper , Dylan Hadfield-Menell , Jacob Andreas

Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation…

Artificial Intelligence · Computer Science 2026-05-26 Ashwath Vaithinathan Aravindan , Mayank Kejriwal

Large Language Models (LLMs) act as powerful reasoning engines but struggle with "symbol grounding" in embodied environments, particularly when information is asymmetrically distributed. We investigate the Privileged Information Bias (or…

Artificial Intelligence · Computer Science 2025-12-19 Shaun Baek , Sam Liu , Joseph Ukpong

Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical…

Artificial Intelligence · Computer Science 2026-03-12 Anita Yang , Krikamol Muandet , Michele Caprio , Siu Lun Chau , Masaki Adachi

Retrieval-Augmented Generation (RAG) shows impressive performance by supplementing and substituting parametric knowledge in Large Language Models (LLMs). Retrieved knowledge can be divided into three types: explicit answer evidence,…

Computation and Language · Computer Science 2025-08-05 Zhichao Yan , Jiapu Wang , Jiaoyan Chen , Yanyan Wang , Hongye Tan , Jiye Liang , Xiaoli Li , Ru Li , Jeff Z. Pan

Unlearning in large language models (LLMs) is crucial for managing sensitive data and correcting misinformation, yet evaluating its effectiveness remains an open problem. We investigate whether persuasive prompting can recall factual…

Computation and Language · Computer Science 2025-10-30 Aakriti Shah , Thai Le

Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore computationally…

Machine Learning · Computer Science 2026-03-09 Azza Jenane , Nassim Walha , Lukas Kuhn , Florian Buettner

Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with "I don't know". Instead, they often produce incorrect…

Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will surpass human expertise, and the role of human evaluation…

Large language models (LLMs) have delivered significant breakthroughs across diverse domains but can still produce unreliable or misleading outputs, posing critical challenges for real-world applications. While many recent studies focus on…

Computation and Language · Computer Science 2025-09-08 Yang Nan , Pengfei He , Ravi Tandon , Han Xu

%Large vision-language models (LVLMs) have shown substantial advances in multimodal understanding and generation. However, when presented with incompetent or adversarial inputs, they frequently produce unreliable or even harmful content,…

Machine Learning · Computer Science 2026-02-27 Tao Huang , Rui Wang , Xiaofei Liu , Yi Qin , Li Duan , Liping Jing

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with…

Computation and Language · Computer Science 2025-08-28 Ramya Keerthy Thatikonda , Wray Buntine , Ehsan Shareghi

Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models. However, the true efficacy of current unlearning methods remains uncertain. Standard evaluation metrics rely on benign queries that often mistake…

Machine Learning · Computer Science 2026-02-09 Patryk Rybak , Paweł Batorski , Paul Swoboda , Przemysław Spurek

Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking methods demonstrate that this alignment can be undermined using…

Cryptography and Security · Computer Science 2023-12-11 Zhuo Zhang , Guangyu Shen , Guanhong Tao , Siyuan Cheng , Xiangyu Zhang

Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation. Existing unlearning methods aim to make the process of…

Cryptography and Security · Computer Science 2025-06-24 Yash Sinha , Manit Baser , Murari Mandal , Dinil Mon Divakaran , Mohan Kankanhalli

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual…

Computation and Language · Computer Science 2022-10-21 Shaobo Li , Xiaoguang Li , Lifeng Shang , Chengjie Sun , Bingquan Liu , Zhenzhou Ji , Xin Jiang , Qun Liu

Large language models (LLMs) are increasingly used in applications requiring factual accuracy, yet their outputs often contain hallucinated responses. While fact-checking can mitigate these errors, existing methods typically retrieve…

Computation and Language · Computer Science 2026-01-07 Haoran Wang , Maryam Khalid , Qiong Wu , Jian Gao , Cheng Cao

Retrieval-augmented large language models (LLMs) have been remarkably competent in various NLP tasks. However, it was observed by previous works that retrieval is not always helpful, especially when the LLM is already knowledgeable on the…

Computation and Language · Computer Science 2024-12-16 Chengkai Huang , Yu Xia , Rui Wang , Kaige Xie , Tong Yu , Julian McAuley , Lina Yao

While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with all the information needed to reach a solution. By contrast,…

Machine Learning · Computer Science 2025-06-11 Zhanke Zhou , Xiao Feng , Zhaocheng Zhu , Jiangchao Yao , Sanmi Koyejo , Bo Han
‹ Prev 1 4 5 6 7 8 10 Next ›