AI
PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training
Researchers have proposed a new framework called PrivAct to improve the privacy of large language mo...
AI
The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI
Researchers have developed a framework to audit latent bias in generative AI models by analyzing the...
AI
Eval4Sim: An Evaluation Framework for Persona Simulation
Researchers have developed an evaluation framework called Eval4Sim for assessing the accuracy of sim...
AI
Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning
Researchers have developed a new framework for automatic speech recognition (ASR) that can handle mu...
AI
N-gram-like Language Models Predict Naturalistic Reading Time Best
Researchers propose that naturalistic reading time can be predicted using simple...
AI
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Researchers have found that self-distillation can sometimes degrade the performa...
AI
ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection
Researchers have developed ContextClaim, a new approach to verifiable claim dete...
AI
DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling
Researchers have developed DataSTORM, a system that uses large language models t...