5 papers
Informational Antilocality and the Locality Bias in LLMs
Andrew McInnerney, Shane Storks, Steven Abney +1
We consider the ability of transformer-based language models (LLMs) to learn what we call k-antilocal languages, i.e., languages that have no mutual information across any span of…
Conflict and Congruency Effects in Large Language Models: In-Weight and In-Context Competition in a Verbal Conflict Task
Xiaoyang Hu, Mike Angstadt, Shane Storks +5
Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neuroscience, but their mechanistic b…
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5
Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insuffic…
Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study
Charlotte S. Alexander, Shane Storks, Souradip Pal +4
Letters of recommendation (LoRs) can carry patterns of implicitly gendered language that can inadvertently influence downstream decisions, e.g. in hiring and admissions. In this wo…
Discovering Properties of Inflectional Morphology in Neural Emergent Communication
Miles Gilberti, Shane Storks, Huteng Dai
Emergent communication (EmCom) with deep neural network-based agents promises to yield insights into the nature of human language, but remains focused primarily on a few subfield-s…