29 citations · 30 across the 17 of their papers we have counts for
10 papers · 1 filter
Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
Jiayi Zhou, David W. Johnston, Brinnae Bent
Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthe…
Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks
Mia Lassiter, Brinnae Bent
The term agent in artificial intelligence lacks a standard definition, complicating the evaluation, comparison, and reproducibility of AI agent research. We address this ambiguity…
Why2Speak: Faithful Reasoning for Abstaining Action Policies
Shreya Mendi, Brinnae Bent
Many agentic systems must repeatedly choose between acting and abstaining, making faithful reasoning important for oversight: an explanation is useful only if it reflects the compu…
Aïra: Rethinking AI Research Assistants for Interdisciplinary Science
Diya Mirji, Tiffany Degbotse, Sharmil Nanjappa +9
Scientific discovery increasingly depends on interdisciplinary teams whose members contribute distinct expertise, conceptual frameworks, vocabularies, assumptions, and standards of…
Explainable AI for Biodiversity Monitoring and Ecological Image Analysis
Brinnae Bent, Holly R. Houliston, Jiayi Zhou +2
Artificial intelligence is transforming biodiversity monitoring by enabling automated analysis of ecological imagery collected from camera traps, drones, satellites, underwater pla…
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt
Stuart Bladon, Brinnae Bent
It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We tested seven open-weight LLM pairs…
Feature Visualization Recovers Known Cortical Selectivity from TRIBE v2
Stuart Bladon, Brinnae Bent
Brain encoder models predict cortical fMRI responses from the internal activations of pretrained vision and language networks, and are typically evaluated by held-out prediction ac…
When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models
Vihaan Nama, Shreya Mendi, Zian Ye +1
Large Language Models (LLMs) excel at generating contextually appropriate responses but remain poorly calibrated for multi-party conversations, where deciding when to speak is as c…
When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
Jiechen Li, Catherine A. Barry, Rishika Randev +3
This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through ex…
GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension
Bochu Ding, Brinnae Bent, Augustus Wendell
Text-to-image (T2I) models, and their encoded biases, increasingly shape the visual media the public encounters. While researchers have produced a rich body of work on bias measure…