Vidhisha Balachandran
Home
Publications
Experience
Talks
CV
Recent & Upcoming Talks
2023
Evaluating and Mitigating Factual Inconsistencies in Language Generation
Despite the large scale of computation and data, current large language models (LLMs) still have a propensity to generate …
Dec 1, 2023
Deep Learning: Classics and Trends - ML Collective
Slides
Actionable Directions for Reporting and Mitigating Language Model Harms
Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in …
Jun 20, 2023
Center for Security and Emerging Technology, Georgetown University
Slides
Generalizable Factual Error Correction of Model Generated Summaries
Abstractive summarization models often generate inconsistent summaries containing factual errors or hallucinated content. Recent works …
May 18, 2023
DARPA SemaFor
Slides
2022
Self Attention and Transformers for Undergrad NLP
Apr 16, 2022
Undergrad NLP at University of Washington
Slides
2021
Simple and Efficient ways to Improve REALM
Dense retrieval has been shown to be effective for retrieving relevant documents for Open Domain QA, surpassing popular sparse …
Jun 1, 2021
Google N2Formal Reading Group
Slides
On the Transparency and Reliability of Automatic Summarization
Internet users today have access to an ocean of information via the Web ranging from news articles to blogs to textbooks. To consume …
Apr 30, 2021
CRIM Seminar Series
Slides
Cite
×