About
Research & Development
GDPval: A New Benchmark for Measuring AI’s Economic Value in Real-World Tasks
TLDR: OpenAI introduces GDPval, a novel benchmark to evaluate AI models on real-world, economically valuable tasks across 44 occupations in top U.S. GDP sectors....
Research & Development
Ensuring Stable Outputs from Retrieval-Augmented AI
TLDR: A new research paper introduces Con-RAG, a reinforcement learning approach that uses Group Relative Policy Optimization (PS-GRPO) to significantly improve information consistency in...
Research & Development
Unmasking LLM Hallucinations: New Method Exposes Vulnerabilities Through Realistic Prompt Variations
TLDR: A new method called SECA (Semantically Equivalent and Coherent Attacks) generates realistic, meaning-preserving prompt variations that significantly increase Large Language Model (LLM) hallucination...
Research & Development
Boosting Transformer Efficiency with Compressed Convolutional Attention
TLDR: Compressed Convolutional Attention (CCA) is a new method that addresses the high computational and memory costs of Multi-headed Attention (MHA) in large language...
Research & Development
GRACE: Enhancing LLM Text Embeddings with Interpretable Reasoning
TLDR: GRACE (Generative Representation Learning via Contrastive Policy Optimization) is a novel framework that reimagines contrastive signals as rewards to guide an LLM's generative...
Research & Development
LaDiR: A Latent Diffusion Approach for Enhanced LLM Reasoning
TLDR: LaDiR (LatentDiffusionReasoner) is a novel framework that improves Large Language Models' (LLMs) text reasoning by unifying continuous latent representations with the iterative refinement...