Enhancing LLM Reliability with Reinforcement Learning
Discover how Deliberative Searcher boosts large language model reliability using reinforcement learning and retrieval-based verification.
Persona-Assigned LLMs Show Human-Like Motivated Reasoning
Study reveals persona-assigned large language models exhibit biased reasoning similar to humans, impacting AI reliability in critical societal issues.
TabularMath: Enhancing Math Reasoning Over Tables with LLMs
Explore TabularMath, a benchmark improving large language models' math reasoning over complex tabular data in real-world scenarios.
Adaptive Dynamic Sampling for Enhanced Math Reasoning AI
Discover SAI-DPO, a dynamic sampling method that adapts training data to model ability, boosting math reasoning performance efficiently.
AI Agents Facing Complex Multi-Objective Decisions
Explore key challenges AI agents face in hard choices, including identification and resolution problems in multi-objective decision-making.