AI
Abliteration Mitigation via Refusal Aliases
Researchers have identified a weakness in large language models called abliteration, where an attack...
AI
NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages
Researchers have developed a multilingual language model called NE-BERT that can process nine Northe...
AI
Backdoor Learning in Language Models and Vision-Language Models
Researchers have identified vulnerabilities in language models and vision-language models that can b...
AI
Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems
Researchers have developed a new caching algorithm called Fractional Decay KV-Cache, designed to imp...
AI
Computational Orientalism: Measuring Structural Discourse Bias in Large Language Models Using the Middle East Cultural Sensitivity Score (MECSS)
Researchers have developed the Middle East Cultural Sensitivity Score (MECSS) to...
AI
DeepTCM1.0: A Multi-Expert AI Agent for Deciphering Mechanisms of Chinese Herbal Formulae Based on General Large Language Models
Researchers have developed DeepTCM1.0, a multi-expert AI agent that can decipher...
AI
StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Data
StocksTalk is a voice-enabled conversational system that can turn spoken financi...
AI
Different Facets of Verbalised Overconfidence: an Interpretability Study
Researchers studied how a large language model called Qwen3-4B expresses confide...