Meihong Wang

LLMs can be made more reliable and efficient by adaptively focusing uncertainty quantification on relevant semantic themes, cutting inference time by 60% while improving factuality correlation.

Unleashing chain-of-thought reasoning on free-form question answering tasks is now possible without manual prompts, thanks to a new decoding strategy that automatically generates and evaluates reasoning paths.

Forget static summarization trees – DTCRS dynamically constructs them based on question type and semantics, slashing construction time and boosting QA accuracy.