Papers by Eric Horvitz
Navigating Rifts in Human-LLM Grounding: Study and Benchmark (2025.acl-long)
Copied to clipboard
| Challenge: | Language models excel at following instructions but struggle with collaborative aspects of conversation that humans naturally employ. |
| Approach: | They analyze logs from WildChat, MultiWOZ, and Bing Chat to examine grounding challenges . they propose a benchmark to determine when LLMs fail to initiate grounding . |
| Outcome: | The proposed model predicts interactions that fail to ground with users . the proposed model is based on human-human interactions with humans . |
SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search (2020.emnlp-demos)
Copied to clipboard
Tom Hope, Jason Portenoy, Kishore Vasan, Jonathan Borchardt, Eric Horvitz, Daniel Weld, Marti Hearst, Jevin West
| Challenge: | SciSight is a system for exploratory search of COVID-19 literature . it explores associations between biomedical facets extracted from papers . |
| Approach: | They propose a system for exploratory search of COVID-19 literature that integrates two key capabilities: first, exploring associations between biomedical facets automatically extracted from papers; second, combining textual and network information to search and visualize groups of researchers and their ties. |
| Outcome: | The proposed system has served over 15K users with over 42K page views and 13% returns. |
Recollection versus Imagination: Exploring Human Memory and Cognition via Neural Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | a dataset of imagined and recalled stories is used to study the cognitive processes involved in storytelling, contrasting imagination and recollection of events. |
| Approach: | They use a dataset of 7,000 stories to study the cognitive processes involved in storytelling, contrasting imagination and recollection of events. |
| Outcome: | The proposed measures show that imagined stories have a substantially more linear narrative flow compared to recalled stories in which adjacent sentences are more disconnected. |
Tandem Training for Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | As language models improve, their actions and reasoning will become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. |
| Approach: | They propose a tandem training paradigm that allows models to adapt their language to weaker partners by intermittently and randomly sampling a frozen weak model instead of the strong model being trained. |
| Outcome: | The proposed model is able to produce solutions that are intelligible to weaker agents and humans while keeping task accuracy high. |
Extracting a Knowledge Base of Mechanisms from COVID-19 Papers (2021.naacl-main)
Copied to clipboard
Tom Hope, Aida Amini, David Wadden, Madeleine van Zuylen, Sravanthi Parasa, Eric Horvitz, Daniel Weld, Roy Schwartz, Hannaneh Hajishirzi
| Challenge: | COVID-19 has spawned a diverse body of scientific literature that is challenging to navigate . researchers are using automated tools to help find useful knowledge . |
| Approach: | They develop a schema to extract mechanism relations from scientific papers . their search engine, dataset and code are publicly available . |
| Outcome: | The proposed schema outperforms PubMed search in clinical trials. |