Papers by Sheshera Mysore
Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity (2022.naacl-main)
Copied to clipboard
| Challenge: | Using co-citations, we can train a model that matches aspects of papers to document level similarity. |
| Approach: | They propose a model that matches fine-grained aspects of papers and aggregates them into a document level similarity model using a naturally-occurring source of supervision: co-citations. |
| Outcome: | The proposed model improves performance on document similarity tasks in four datasets and achieves competitive results. |
Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rather than passively accepting output, users actively refine, explore, and co-construct text. |
| Approach: | They conduct a large scale analysis of user-LLM collaboration behavior with two popular AI assistants, Bing Copilot and WildChat. |
| Outcome: | The proposed models show that a small group of prototypical human AI collaboration behaviors explain a majority of the variation seen in user-LLM interaction. |
MS-Mentions: Consistently Annotating Entity Mentions in Materials Science Procedural Text (2021.emnlp-main)
Copied to clipboard
Tim O’Gorman, Zach Jensen, Sheshera Mysore, Kevin Huang, Rubayyat Mahbub, Elsa Olivetti, Andrew McCallum
| Challenge: | Material science synthesis procedures require high-quality annotations, which are limited by the size and quality of the annotations. |
| Approach: | They propose a corpus of entity mention annotations over 595 Material Science synthesis procedures. |
| Outcome: | The proposed approach greatly expands the training data available for the Named Entity Recognition task. |
An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to parse scientific text using grammatically similar labeled sentences are limited and expensive to create. |
| Approach: | They propose a method where semantic labels from structurally similar sentences are copied to test sentences. |
| Outcome: | The proposed approach outperforms baseline and prior methods by 0.75 to 3 F1 absolute in the wet lab protocol corpus and 1 F1 absolut in the materials science procedural text corpus. |
LaMP: When Large Language Models Meet Personalization (2024.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for personalization in large language models are understudied . |
| Approach: | They propose a benchmark for training and evaluating language models for producing personalized outputs using a set of seven personalized tasks . they propose two retrieval augmentation approaches that retrieve personal items from each user profile for personalizing language model outputs. |
| Outcome: | The proposed approach is effective for a set of zero-shot and fine-tuned language models and highlights the impact of personalization in various natural language tasks. |