Related papers: Consistency Amplifies: How Behavioral Variance Sha…

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpful-only training objective to prevent modification of their behavior outside of training. We expand…

Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problems or specific…

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…

Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this consistency in the generation? We investigate this phenomenon through the lens of probability…

Large Language Models (LLMs) are increasingly applied to software engineering (SE), yet their potential for autonomous, role-oriented collaboration remains largely underexplored. Understanding how multiple LLM-based agents coordinate,…

As language models (LMs) are increasingly deployed as autonomous agents, their robust adherence to human-assigned objectives becomes crucial for safe operation. When these agents operate independently for extended periods without human…

Structured deliberation has been found to improve the performance of human forecasters. This study investigates whether a similar intervention, i.e. allowing LLMs to review each other's forecasts before updating, can improve accuracy in…

Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…

Generative artificial intelligences, particularly large language models (LLMs), play an increasingly prominent role in human decision-making contexts, necessitating transparency about their capabilities. While prior studies have shown…

Deep learning classifiers are assisting humans in making decisions and hence the user's trust in these models is of paramount importance. Trust is often a function of constant behavior. From an AI model perspective it means given the same…

Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlying semantic meaning, can significantly affect their…

This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench…

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to…

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their…

Vision-Language-Action (VLA) models have shown strong performance on embodied manipulation, yet they remain brittle under visual observation changes, paraphrased language instructions, and compounded perturbations. This limitation suggests…

Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer through majority…

Recent works have demonstrated great success in pre-training large-scale autoregressive language models on massive GPUs. To reduce the wall-clock training time, a common practice is to increase the batch size and learning rate. However,…

Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistency…

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…

Large language models (LLMs) are increasingly deployed in agentic and multi-turn workflows where they are tasked to perform actions of significant consequence. In order to deploy them reliably and manage risky outcomes in these settings, it…