Papers by Oren Sultan

4 papers
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs (2022.emnlp-main)

Copied to clipboard

Challenge: a framework for language understanding models to track and improve beliefs through intermediate points in text is needed . breakpoint modeling is an efficient and end-to-end learning approach that trains models to train beliefs . understanding the behavior of models remains a formidable challenge for model safety, authors say .
Approach: They propose a framework that trains models to track beliefs through intermediate points in text . their framework allows for efficient and robust learning of this type of model .
Outcome: The proposed model outperforms strong representation learning approaches on a variety of NLU tasks.
Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes (2022.emnlp-main)

Copied to clipboard

Challenge: Analogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference – abilities that current AI systems lack.
Approach: They propose an interpretable, scalable algorithm that extracts analogies from a pair of natural language procedural texts and finds a mapping between the different domains based on relational similarity.
Outcome: The proposed algorithm can extract analogies from a large dataset and achieve 79% precision.
ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies (2024.naacl-long)

Copied to clipboard

Challenge: Analogy-making is a central to human cognition, allowing us to abstract information and understand novel situations in terms of familiar ones.
Approach: They propose a pipeline to generate paragraph-based analogies using large language models and large language distractors.
Outcome: The proposed pipeline outperforms existing models in binary and multiple-choice settings and shows that humans outperformed the best models after a light supervision.
Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications (2024.emnlp-industry)

Copied to clipboard

Challenge: Using natural language as an interaction medium for video editing can mitigate the complexity of video editing.
Approach: They propose a method to fine-tune LLMs for invoking tools in real-time applications by interpreting user stylistic requests in natural language.
Outcome: The proposed model matches the performance of the teacher model significantly, reducing costs and latency.

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