AI
ArborMem: Navigating Interaction States with Memory Forests
Researchers have developed a new memory framework called ArborMem that can navigate complex conversa...
AI
Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study
Researchers from France, Italy, and Sweden conducted an audit of TikTok's content using multimodal l...
AI
Write, Execute, Refine: From Skill Followers to Skill Optimizers via Reinforcement Learning from Execution Feedback
Researchers have developed a framework called WER (Write, Execute, and Refine) that uses reinforceme...
AI
Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See
Researchers fine-tuned three large-scale AI models to reason in a low-resource language, specificall...
AI
Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility
Researchers have been studying how machine learning systems make decisions based...
AI
TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification
Researchers have developed a new model called TraceSQL for verifying the correct...
AI
Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It
Researchers have found that large language models (LLMs) struggle to navigate be...
AI
From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector
Researchers have created a new framework to evaluate language models for use in ...