5 papers
Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media
Scott Friedman, Ruta Wheelock, Sonja Schmer-Galunder +6
The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpfulness, compassion) and anti-s…
Where Norms and References Collide: Evaluating LLMs on Normative Reasoning
Mitchell Abrams, Kaveh Eskandari Miandoab, Felix Gervits +2
Embodied agents, such as robots, will need to interact in situated environments where successful communication often depends on reasoning over social norms: shared expectations tha…
IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection
Kaveh Eskandari Miandoab, Katharine Kowalyshyn, Kabir Pamnani +3
We present IntelliProof, an interactive system for analyzing argumentative essays through LLMs. IntelliProof structures an essay as an argumentation graph, where claims are represe…
Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation
Kaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni +3
Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been tra…
Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
Panagiotis Lymperopoulos, Vasanth Sarathy
Modern Large Language Models (LLMs) often require external tools, such as machine learning classifiers or knowledge retrieval systems, to provide accurate answers in domains where…