Related papers: Alignment Debt: The Hidden Work of Making AI Usabl…

Real-effort tasks, in which participants perform cognitively costly activities whose outcomes depend on actual performance, are widely used in experimental economics. Their validity, however, rests on the assumption that a human performs…

Artificial Intelligence (AI) tools for automating design artifact generation are increasingly used in Requirements Engineering (RE) to transform textual requirements into structured diagrams and models. While these AI tools, particularly…

The capabilities of artificial intelligence (AI) lie along a jagged frontier, where AI systems surprisingly fail on tasks that humans find easy and succeed on tasks that humans find hard. To investigate user reactions to this phenomenon, we…

Self-Admitted Technical Debt (SATD) refers to technical compromises explicitly admitted by developers in natural language artifacts such as code comments, commit messages, and issue trackers. Among its types, Architecture Technical Debt…

Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks,…

A surge of recent work explores the ethical and societal implications of large-scale AI models that make "moral" judgments. Much of this literature focuses either on alignment with human judgments through various thought experiments or on…

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

AI coding assistants are now widely used in software development. Software developers increasingly integrate AI-generated code into their codebases to improve productivity. Prior studies have shown that AI-generated code may contain code…

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Artificial Intelligence (AI), particularly large language models (LLMs), holds the potential to bridge language and information gaps, which can benefit the economies of developing nations. However, our analysis of FLORES-200, FLORES+,…

This paper addresses the question of how to align AI systems with human values and situates it within a wider body of thought regarding technology and value. Far from existing in a vacuum, there has long been an interest in the ability of…

Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk…

Aligning AI agents to human intentions and values is a key bottleneck in building safe and deployable AI applications. But whose values should AI agents be aligned with? Reinforcement learning with human feedback (RLHF) has emerged as the…

This report examines a novel risk associated with current (and projected) AI tools. Making effective decisions about future actions requires us to reason under uncertainty (RUU), and doing so is essential to many critical real world…

Multilingual large language models (LLMs) face an often-overlooked challenge stemming from intrinsic semantic differences across languages. Linguistic divergence can sometimes lead to cross-linguistic disagreements--disagreements purely due…

In early developmental contexts, particularly in parent-child interaction analysis, alignment involves families and professionals such as speech-language pathologists (SLPs) who interpret children's everyday interactions from different…

The AI alignment problem comprises both technical and normative dimensions. While technical solutions focus on implementing normative constraints in AI systems, the normative problem concerns determining what these constraints should be.…

Prior work has mapped which workplace tasks are exposed to AI, but less is known about whether workers perceive these tasks as meaningful or as busywork. We examined: (1) which dimensions of meaningful work do workers associate with tasks…

Human feedback plays a pivotal role in aligning large language models (LLMs) with human preferences. However, such feedback is often noisy or inconsistent, which can degrade the quality of reward models and hinder alignment. While various…