AI
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
Researchers have developed a framework called Verifiable Latent Alignments (VLA) to detect and preve...
AI
SuTRA : Structurally-Unified Tokenization with Root Awareness
Researchers propose SuTRA (Structurally-Unified Tokenization with Root Awareness), an algorithm that...
AI
Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without Retraining
Researchers have developed a method called Latent Space Refusal Anchoring (LSR-Anchoring) to help AI...
AI
Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities
Researchers have developed a method to identify an internal 'valence axis' in language models that t...
AI
Self- and Other-Labels Induce Bidirectional Bias in LLM Judges
Researchers have found that language models (LLMs) exhibit bias when judging the...
AI
Abliteration Mitigation via Refusal Aliases
Researchers have identified a weakness in large language models called abliterat...
AI
NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages
Researchers have developed a multilingual language model called NE-BERT that can...
AI
Backdoor Learning in Language Models and Vision-Language Models
Researchers have identified vulnerabilities in language models and vision-langua...