Papers by Sheshera Mysore

5 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations