Contextual Pictograms for Repairing Multilingual ASR Errors
Research
Research News
New papers, breakthroughs and academic AI research
Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis
Research
Prospective Memory for Proactive LLM Agents
Research
How Well Can Large Language Models Impersonate Individual Authors? A Comparative Evaluation
Research
Learning When Human Decisions Matter: Executor-Relative Consultation Value for LLM Agents
Research
Phonological Knowledge of Chinese Characters in Language Models
Research
Matching the Training-Time Weight Rule in Inference-Time Expert Deactivation
Research
CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines
Research
When Does Better Confidence Improve a Knowledge-Graph Audit?
Research
Verified but Vacuous: Three Failure Surfaces of LLM-Driven Verified Code Generation
Research
Anduin: A sybil-resistant agentic marketplace reputation system
Research
Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation
Research