Papers by Alon Halevy
NormBank: A Knowledge Bank of Situational Social Norms (2023.acl-long)
Copied to clipboard
| Challenge: | NormBank is a knowledge bank of 155k situational norms that can be used to ground flexible normative reasoning for interactive, assistive, and collaborative AI systems. |
| Approach: | They propose a new scheme for hierarchically organizing the seemingly unbounded social norms within a multivalent sociocultural frame. |
| Outcome: | The proposed framework can be used to ground flexible reasoning for interactive, assistive, and collaborative AI systems. |
The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems (2022.acl-long)
Copied to clipboard
| Challenge: | Moral integrity corpus captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs). |
| Approach: | They propose a resource that captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs). |
| Outcome: | The proposed resource captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs). |
Quantifying Adaptability in Pre-trained Language Models with 500 Tasks (2022.naacl-main)
Copied to clipboard
| Challenge: | a recent study examines the features and limits of LM adaptability to new tasks . many questions about the nature and limits remain unanswered . |
| Approach: | They evaluate adaptability to new tasks using a new benchmark, TaskBench500 . they find adaptation procedures differ dramatically in their ability to memorize small datasets . |
| Outcome: | The proposed benchmark compares 500 procedurally generated sequence modeling tasks to a new benchmark. |
TimelineQA: A Benchmark for Question Answering over Timelines (2023.findings-acl)
Copied to clipboard
Wang-Chiew Tan, Jane Dwivedi-Yu, Yuliang Li, Lambert Mathias, Marzieh Saeidi, Jing Nathan Yan, Alon Halevy
| Challenge: | Existing question answering techniques for lifelogs do not provide accurate answers . augmented reality glasses have led to the creation of personal assistants . |
| Approach: | They propose to use a benchmark to query lifelogs to find out what happened in real life . they find that extractive QA systems out-perform retrieval-augmented QA techniques . |
| Outcome: | The proposed method outperforms state-of-the-art retrieval-augmented QA systems in atomic queries and multi-hop queries. |
Database reasoning over text (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models cannot handle database queries such as “List/Count all female athletes who were born in 20th century”. |
| Approach: | They propose a modular architecture to answer database-style queries over multiple spans from text and aggregate them at scale. |
| Outcome: | The proposed architecture scales to databases containing thousands of facts whereas current models are limited by how many facts can be encoded. |
HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments (L18-1)
Copied to clipboard
Akari Asai, Sara Evensen, Behzad Golshan, Alon Halevy, Vivian Li, Andrei Lopatenko, Daniela Stepanov, Yoshihiko Suhara, Wang-Chiew Tan, Yinzhan Xu
| Challenge: | Recent research has focused on developing technologies that help users incorporate the findings of the science of happiness into their daily lives. |
| Approach: | They crowd-sourced HappyDB, a corpus of 100,000 happy moments, and applied several state-of-the-art analysis techniques to analyze HappyDB. |
| Outcome: | The proposed technology can understand how people express their happy moments in text and analyze them using state-of-the-art techniques. |
Open Information Extraction from Question-Answer Pairs (N19-1)
Copied to clipboard
| Challenge: | Existing work on OpenIE extracts structured data from sentences . a system for extracting tuples from question-answer pairs solves this problem . |
| Approach: | They propose a system for extracting tuples from question-answer pairs . they use distributed representations of a question and an answer to generate knowledge facts . |
| Outcome: | The proposed system extracts meaningful structured tuples from question-answer pairs . it can find new and interesting facts to extend knowledge bases, the authors show . |
Reimagining Retrieval Augmented Language Models for Answering Queries (2023.findings-acl)
Copied to clipboard
Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, Wen-tau Yih
| Challenge: | Large language models (LLMs) are expensive to train, deploy, and maintain, both financially and in terms of environmental impact. |
| Approach: | They present a reality check on large language models and compare their predictions to retrieval-augmented language models. |
| Outcome: | The proposed models fare better on question answering tasks and have become the foundation of impressive demos like Chat-GPT. |