Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment Mon, 21 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30 Mon, 21 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generation Mon, 21 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
AI Should Facilitate Democratic Deliberation at Scale Fri, 18 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence Fri, 18 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS Fri, 18 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Mitigating Fabrication in Multi-Stage LLM Pipelines for Hiring: An Empirical Evaluation of Prompt Guardrails and Human-in-the-Loop Checkpoints Fri, 18 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Language-model groups overstate consensus when replaying human deliberation on a reasoning task Fri, 18 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Understanding AI Provider Recommendations in Local Service Markets Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Mind the Style: Impact of Communication Style on Human-Chatbot Interaction Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems Thu, 17 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
How Humans and LLMs Read Gender into Gender-Neutral Physical Descriptions Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Acoustic and perceptual differences between standard and accented speech and their voice clones Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Disrupted Companionship: A Risk Assessment Framework and Cross-Platform Quantitative Analysis of Psychosocial Responses to AI Companion Disruptions Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society
Towards Detecting AI-Assisted Responses in Online Surveys Wed, 16 Sep 2026 00:00:00 -0400 · arXiv: Computers and Society