Related papers: Probing and Steering Evaluation Awareness of Langu…

Trustworthy machine learning is of primary importance to the practical deployment of deep learning models. While state-of-the-art models achieve astonishingly good performance in terms of accuracy, recent literature reveals that their…

Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address…

It has been reported that LLMs can recognize their own writing. As this has potential implications for AI safety, yet is relatively understudied, we investigate the phenomenon, seeking to establish whether it robustly occurs at the…

Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM's capability to withhold responses when uncertain or lacking a definitive answer, without compromising performance. Although…

The use of large language model (LLM)-powered chatbots, such as ChatGPT, has become popular across various domains, supporting a range of tasks and processes. However, due to the intrinsic complexity of LLMs, effective prompting is more…

Large language models have increasingly been proposed as a powerful replacement for classical agent-based models (ABMs) to simulate social dynamics. By using LLMs as a proxy for human behavior, the hope of this new approach is to be able to…

Large Language Models (LLMs) hold promise as dynamic instructional aids. Yet, it remains unclear whether LLMs can replicate the adaptivity of intelligent tutoring systems (ITS)--where student knowledge and pedagogical strategies are…

Before adopting a new large language model (LLM) architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

Large language models (LLMs) are increasingly applied in computer science education for tasks such as tutoring, content generation, and code assessment. However, systematic evaluations aligned with formal curricula and certification…

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…

We investigate the calibration of large language models' (LLMs') confidence across diverse tasks. The results of our preregistered study show that the current crop of LLMs are, like people, too sure they are right: confidence exceeds…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Forming a reliable judgement of a machine learning (ML) model's appropriateness for an application ecosystem is critical for its responsible use, and requires considering a broad range of factors including harms, benefits, and…

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…

Language models often struggle with handling factual knowledge, exhibiting factual hallucination issue. This makes it vital to evaluate the models' ability to recall its parametric knowledge about facts. In this study, we introduce a…

With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in LLMs' safety alignment, it remains unclear whether LLMs have…

Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of reasoning: efficiency. In real-world reasoning scenarios, much of the available…

Large language models (LLMs) are increasingly deployed across high-impact domains, from clinical decision support and legal analysis to hiring and education, making fairness and bias evaluation before deployment critical. However, existing…

We investigate a surprising limitation of LLMs: their inability to consistently generate text in a user's desired language. We create the Language Confusion Benchmark (LCB) to evaluate such failures, covering 15 typologically diverse…