1

Intention-Adaptive LLM Fine-Tuning for Text Revision Generation

Large Language Models (LLMs) have achieved impressive capabilities in various context-based text generation tasks, such as …

Zhexiong Liu, Diane Litman

Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction

Large Language Models (LLMs) have shown extraordinary success across various text generation tasks; however, their potential for simple …

Zhexiong Liu, Diane Litman

eRevise+RF: A Writing Evaluation System for Assessing Student Essay Revisions and Providing Formative Feedback

The ability to revise essays in response to feedback is important for students’ writing success. An automated writing evaluation (AWE) …

Zhexiong Liu, Diane Litman, Elaine Lin Wang, Tianwen Li, Mason Gobat, Lindsay C. Matsumura, Richard Correnti

A Tale of Evaluating Factual Consistency: Case Study on Long Document Summarization Evaluation

Yang Zhong, Diane Litman

Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization

Yang Zhong, Diane Litman

From Information to Insight: Leveraging LLMs for Open Aspect-Based Educational Summarization

Yang Zhong, Diane Litman

Analyzing Large Language Models for Classroom Discussion Assessment

Nhat Tran, Benjamin Pierce, Diane Litman, Richard Correnti, Lindsay Clare Matsumura

Using Large Language Models to Assess Young Students′ Writing Revisions

Although effective revision is the crucial component of writing instruction, few automated writing evaluation (AWE) systems …

Tianwen Li, Zhexiong Liu, Lindsay Matsumura, Elaine Wang, Diane Litman, Richard Correnti

Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions

Human evaluation remains the gold standard for assessing abstractive summarization. However, current practices often prioritize …

Mohamed Elaraby, Huihui Xu, Morgan Gray, Kevin Ashley, Diane Litman

Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue

Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural …

Nhat Tran, Diane Litman