AI
SynFlow: A Multidimensional Diachronic Semantic Analysis Toolkit
Researchers have developed SynFlow, an open-source toolkit for analyzing how language usage changes ...
AI
Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does
Researchers have developed a new benchmark called Hear2Act to evaluate how prosody affects task-orie...
AI
Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems
Researchers from Japan have developed a method to automatically generate diverse personas for user s...
AI
Reliable Financial Named Entity Recognition under Domain Shift
Researchers have developed a method to improve financial named entity recognition (NER) under domain...
AI
Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents
Researchers propose a framework for evaluating the memory commitment of large la...
AI
Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
Researchers have developed a new framework called LifeMem to improve the perform...
AI
ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents
Researchers have developed ReCache, a framework that improves the efficiency of ...
AI
The Asymmetric Harms of LLM Compression
Researchers have found that compressing large language models (LLMs) can lead to...