Related papers: Self-Attribution Bias: When AI Monitors Go Easy on…
Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…
Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias, which…
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…
Agentic AI increasingly intervenes proactively by inferring users' situations from contextual data yet often fails for lack of principled judgment about when, why, and whether to act. We address this gap by proposing a conceptual model that…
AI services are known to have unstable behavior when subjected to changes in data, models or users. Such behaviors, whether triggered by omission or commission, lead to trust issues when AI works with humans. The current approach of…
Decisions made by machine learning systems have increasing influence on the world, yet it is common for machine learning algorithms to assume that no such influence exists. An example is the use of the i.i.d. assumption in content…
AI-related incidents are becoming increasingly frequent and severe, ranging from safety failures to misuse by malicious actors. In such complex situations, identifying which elements caused an adverse outcome, the problem of cause…
Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicitly mark the source of each piece of context. While these tags are essential for instruction…
We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of acting in place of the agent…
Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure. Recent advances in large language…
This essay identifies a failure mode of AI chat systems that we term attribution laundering: the model performs substantive cognitive work and then rhetorically credits the user for having generated the resulting insights. Unlike…
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…
Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the biased behavior of each component in a TOD system and the…
The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within. A biased model can then make decisions that disproportionately harm certain groups in society. Much…
The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…
Generative AI blurs the lines of authorship in computing education, creating uncertainty around how students should attribute AI assistance. To examine these emerging norms, we conducted a factorial vignette study with 94 computer science…
Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…
The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness is often…
Feature attribution explains neural network outputs by identifying relevant input features. The attribution has to be faithful, meaning that the attributed features must mirror the input features that influence the output. One recent trend…