About
Research & Development
LLMs Learn to Ask Smart Questions for Better Recommendations
TLDR: A new research paper introduces a novel method for training Large Language Models (LLMs) to ask sequential, clarifying questions to effectively elicit user...
Research & Development
Learning World Rules from a Single Exploration in Unpredictable Environments
TLDR: ONELIFE is a new AI framework that learns symbolic world models in complex, stochastic environments with limited, unguided exploration. It uses conditionally-activated programmatic...
Research & Development
Mathematicians Gain a Research Companion with O-Forge
TLDR: O-Forge is a new AI tool that combines large language models (LLMs) with computer algebra systems (CAS) to rigorously prove complex asymptotic inequalities....
Research & Development
Unmasking AI Judge Biases in Communication Systems: A Deep Dive into LLM Evaluation Fairness
TLDR: This research paper investigates biases in LLM-as-a-judge models (GPT-Judge and JudgeLM) used in communication systems. It identifies 11 types of implicit and explicit...
Research & Development
Enhancing AI Reliability: A New Method for Detecting Unexpected Data
TLDR: This paper introduces a novel self-supervised learning approach for Out-of-Distribution (OOD) detection, crucial for making AI systems more robust. By combining self-supervised contrastive...
Research & Development
Ax-Prover: Advancing Automated Theorem Proving Across Science with LLM Agents
TLDR: Ax-Prover is a new multi-agent system that combines large language models (LLMs) with Lean proof assistant tools to perform automated theorem proving. It...