Related papers: BAS: A Decision-Theoretic Approach to Evaluating L…

Offering a promising solution to the scalability challenges associated with human evaluation, the LLM-as-a-judge paradigm is rapidly gaining traction as an approach to evaluating large language models (LLMs). However, there are still many…

Automated speaking assessment (ASA) on opinion expressions is often hampered by the scarcity of labeled recordings, which restricts prompt diversity and undermines scoring reliability. To address this challenge, we propose a novel training…

Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is assessing the validity of the benchmarks themselves. This is…

Automated short-answer grading (ASAG) remains a challenging task due to the linguistic variability of student responses and the need for nuanced, rubric-aligned partial credit. While Large Language Models (LLMs) offer a promising solution,…

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or…

As artificial intelligence (AI) systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well…

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

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…

Large Language Models (LLMs) increasingly rely on long-form, multi-step reasoning to solve complex tasks such as mathematical problem solving and scientific question answering. Despite strong performance, existing confidence estimation…

Behavioral evaluation is the dominant paradigm for assessing alignment in large language models (LLMs). In current practice, observed compliance under finite evaluation protocols is treated as evidence of latent alignment. However, the…

The use of Large Language Models (LLMs) in police operations is growing, yet an evaluation framework tailored to police operations remains absent. While LLM's responses may not always be legally incorrect, their unverified use still can…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Large Language Models (LLMs) have demonstrated remarkable performance across a broad spectrum of tasks, including natural language understanding, dialogue systems, and code generation. Despite evident progress, less attention has been paid…

There is an increasing interest in using language models (LMs) for automated decision-making, with multiple countries actively testing LMs to aid in military crisis decision-making. To scrutinize relying on LM decision-making in high-stakes…

This paper investigates the ability of large language models (LLMs) to solve statistical tasks, as well as their capacity to assess the quality of reasoning. While state-of-the-art LLMs have demonstrated remarkable performance in a range of…

Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM…

A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and…

Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…

As Large Language Models become integral to decision-making, optimism about their power is tempered with concern over their errors. Users may over-rely on LLM advice that is confidently stated but wrong, or under-rely due to mistrust.…