AI
SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation
SIDScope is a diagnostic tool for evaluating the quality of semantic-ID interfaces in generative rec...
AI
Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study
Researchers have studied the performance of majority voting in Large Language Models (LLMs) to impro...
AI
Forgetting, plasticity, and co-observation: a third facet of continual learning
Researchers have identified a new challenge in continual learning for deep neural networks: data co-...
AI
A strengthening of the MCFL-ness of $O_2$
Researchers have strengthened a proof that $O_2$ is a multiple context-free grammar (MCFG). This typ...
AI
Do Large Language Models Hallucinate Electric Fata Morganas?
Researchers have investigated the phenomenon of 'hallucinations' in large langua...
AI
Identifying Implicit Premises for Logical Reconstruction of Argument Graphs
Researchers have proposed a method for identifying implicit premises in argument...
AI
Understanding Multilingual Medical ASR Adaptation Through Layer-Wise Analysis
Researchers analyzed how multilingual medical adaptation affects the internal re...
AI
MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
Researchers propose a new framework for designing reward functions in reinforcem...