Papers by H. Jagadish
Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. |
| Approach: | They propose a Learnable Intervention method for Truthfulness Optimization that automatically identifies the optimal intervention intensity tailored to each query context. |
| Outcome: | Experiments on multiple LLMs and question-answering datasets show that LITO improves truthfulness while preserving task accuracy. |
CompactIE: Compact Facts in Open Information Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Despite advances in open information extraction, many systems focus on covering more information over compactness of constituents. |
| Approach: | They propose a neural OpenIE system that produces compact extractions with overlapping constituents by using a pipelined approach. |
| Outcome: | The proposed system produces 1.5x-2x more compact extractions than previous systems, with high precision, establishing a new state-of-the-art in OpenIE. |