Related papers: Dead Cognitions: A Census of Misattributed Insight…
Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the absence of attribution ground truth to model predictions. In…
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…
Generative AI acts as a disruptive technological shock to evaluative organizations. In academic peer review, it enters both sides of the market: authors use AI to polish submissions, and reviewers use it to generate plausible reports…
We study the tendency of AI systems to deceive by constructing a realistic simulation setting of a company AI assistant. The simulated company employees provide tasks for the assistant to complete, these tasks spanning writing assistance,…
As AI systems increasingly take on instructional roles - providing feedback, guiding practice, evaluating work - a fundamental question emerges: does it matter to learners who they believe is on the other side? We investigated this using a…
As AI writing tools become widespread, we need to understand how both humans and machines evaluate literary style, a domain where objective standards are elusive and judgments are inherently subjective. We conducted controlled experiments…
A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for transparency and…
Online questionnaires that use crowd-sourcing platforms to recruit participants have become commonplace, due to their ease of use and low costs. Artificial Intelligence (AI) based Large Language Models (LLM) have made it easy for bad actors…
Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…
Consumers are increasingly delegating purchase decisions to AI agents, providing natural-language descriptions of their preferences and identity. We argue that these representations constitute an information channel, role coherence, through…
The purpose of this paper is to analyse the opacity of algorithms, contextualized in the open debate on responsibility for artificial intelligence causation; with an experimental approach by which, applying the proposed conversational…
The growing reliance on prediction markets as epistemic infrastructures has positioned platforms like Polymarket as providers of objective, real-time probabilistic truth, yet the signals they produce often obscure uncertainty, strategic…
Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content…
Socially fluent agentic AI can now participate in online interaction in ways that resemble ordinary human conversation, potentially weakening people's ability to infer who is human from conversational signals alone. We tested this…
Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language…
Artificial intelligence systems are increasingly integrated into writing processes, challenging traditional notions of authorship, responsibility, and intellectual contribution. Current disclosure practices usually indicate whether AI was…
High-stakes applications rely on combining Artificial Intelligence (AI) and humans for responsive and reliable decision making. For example, content moderation in social media platforms often employs an AI-human pipeline to promptly remove…
When AI systems summarize and relay information, they inevitably transform it. But how? We introduce an experimental paradigm based on the telephone game to study what happens when AI talks to AI. Across five studies tracking content…
Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content. However, as these tools become increasingly accessible, they also…
Describing our interaction with Artificial Intelligence (AI) systems as 'collaboration' is well-intentioned, but flawed. Not only is it misleading, but it also takes away the credit of AI 'labour' from the humans behind it, and erases and…