Papers by Diane Litman
Automated Topical Component Extraction Using Neural Network Attention Scores from Source-based Essay Scoring (2020.acl-main)
Copied to clipboard
| Challenge: | Automated essay scoring (AES) can grade essays at scale, while automated writing evaluation (AWE) does not provide useful feature representations for supporting AWE. |
| Approach: | They propose a method for linking AWE and neural AES by extracting Topical Components (TCs) representing evidence from a source text using the intermediate output of attention layers. |
| Outcome: | The proposed system is comparable to existing AWE systems for grading essays and representing essays as rubric-based features. |
Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a new study explores data manipulation techniques for improving abstractive summarization models without the need for any additional data. |
| Approach: | They propose a method of data synthesis with paraphrasing, data augmentation with sample mixing and curriculum learning with new difficulty metrics based on specificity and abstractiveness. |
| Outcome: | The proposed techniques improve abstractive summarization models without additional data . the proposed techniques can be applied in isolation and when combined . |
The Discussion Tracker Corpus of Collaborative Argumentation (2020.lrec-1)
Copied to clipboard
| Challenge: | The Discussion Tracker corpus is an annotated dataset of transcripts of spoken, multi-party argumentation transcribed from 985 minutes of audio . |
| Approach: | They analyze 29 multi-party arguments transcribed from 985 minutes of audio . they provide descriptive statistics and code for predicting each dimension separately. |
| Outcome: | The Discussion Tracker corpus was collected in high school English classes and annotated for argument moves, specificity, specificities and collaboration dimensions. |
Exploring Multitask Learning for Low-Resource Abstractive Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work shows that training text encoders using data from multiple tasks helps to produce an encoder that can be used in numerous downstream tasks with minimal fine-tuning. |
| Approach: | They incorporate four different tasks to improve abstractive summarization performance . they use a pretrained BERT model and train all tasks using a small-scale training corpus . |
| Outcome: | The proposed model outperforms a model trained in a multitask setting with no additional summarization data. |
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models have shown extraordinary success across text generation tasks . however, their potential for simple yet essential text classification remains underexplored . |
| Approach: | a plug-and-play layer-wise parameter-efficient fine-tuning framework is proposed . it fine- tunes a subset of important LLM layers while freezing redundant ones . |
| Outcome: | a plug-and-play framework fine-tunes a subset of important LLM layers while freezing redundant layers. |
ARC: Argument Representation and Coverage Analysis for Zero-Shot Long Document Summarization with Instruction Following LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Argument Representation Coverage (ARC) assesses how well summaries preserve salient arguments . despite their fluency, LLMs frequently hallucinate or omit key content . |
| Approach: | They propose an evaluation framework that assesses how well summaries preserve salient arguments . they use argument representation coverage to distinguish between different information types . |
| Outcome: | The proposed framework assesses how well summaries preserve salient arguments . the authors show that LLMs capture some salient roles but omit critical information . |
ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining (2022.coling-1)
Copied to clipboard
| Challenge: | Existing abstractive summarization models do not take into account argumentative structure of legal documents, which poses a challenge towards effective abstractive summary. |
| Approach: | They propose a technique that integrates argument role labeling into the summarization process by integrating argument role labels into the document. |
| Outcome: | The proposed method improves over strong baselines with pretrained language models. |
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI (2025.coling-industry)
Copied to clipboard
Yuya Asano, Sabit Hassan, Paras Sharma, Anthony B. Sicilia, Katherine Atwell, Diane Litman, Malihe Alikhani
| Challenge: | Existing ASR correction methods rely on prior user data or named entities . Existing methods based on prior data are not available for goal-oriented dialogues . |
| Approach: | They propose a method that integrates contextual information from the dialogue states of a goal-oriented conversational AI and its tasks into a large language model. |
| Outcome: | The proposed method improves recall and F1 of correction by 34% and 16% while maintaining precision and false positive rate. |
Intention-Adaptive LLM Fine-Tuning for Text Revision Generation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing work on large language models (LLMs) has demonstrated impressive capabilities in context-based text generation tasks, such as summarization and reasoning. |
| Approach: | They propose an intention-adaptive layer-wise LLM fine-tuning framework that dynamically selects a subset of LLM layers to learn intentions and transfers them to revision generation. |
| Outcome: | The proposed framework outperforms PEFT baselines on small revision corpora while maintaining fast convergence and accuracy. |
Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on generating free-text rationales has focused on tasks where there is an expected factual ground truth. |
| Approach: | They analyze generated free-text rationales in tasks with subjective answers . they find open-source LLMs generate highly persuasive rationale models . |
| Outcome: | The proposed model outperforms closed-source models in pairwise argument ranking, a highly subjective task with potential for debate assistance. |
Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to knowledge retrieval are limited by the knowledge base encoder, but our work focuses on the knowledge-base encoder. |
| Approach: | They propose an approach that utilizes topic modeling on the knowledge base to improve retrieval accuracy and as a result, improve response generation. |
| Outcome: | The proposed approach can improve retrieval and generation performance on two datasets. |
Can LLMs simulate the same correct solutions to free-response math problems as real students? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have explored modeling student mistakes, but lack of understanding of how they generate correct solutions. |
| Approach: | They compare distribution of correct solutions produced by four large language models with students' responses to free-response problems. |
| Outcome: | The proposed model can generate correct solutions that represent student responses to free-response problems. |
Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing summarization systems can generate fluent summaries, but their ability to produce factually consistent summary remains questionable. |
| Approach: | They propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by NLI models. |
| Outcome: | The proposed framework shows better performance over multiple benchmarks, focusing on long document summarization. |
Predicting Desirable Revisions of Evidence and Reasoning in Argumentative Writing (2023.findings-eacl)
Copied to clipboard
| Challenge: | Using the essay context of the revision and feedback from students prior to the revision, we identify desirable and undesirable revisions. |
| Approach: | They propose to use the essay context of the revision and the feedback students received before the revision to improve classifier performance. |
| Outcome: | The proposed models improve over baseline models, while models utilizing context improve over the baseline models. |
Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing summarization models struggle to accurately capture the main arguments of long legal opinions, leading to suboptimal summaries. |
| Approach: | They propose a framework for abstractive summarization of long legal opinions that takes into account the argument structure of the document and reranks them based on alignment with the document's argument structure. |
| Outcome: | The proposed approach outperforms several strong baselines on a dataset of long legal opinions and outperformed existing models. |
A Tale of Evaluating Factual Consistency: Case Study on Long Document Summarization Evaluation (2025.findings-acl)
Copied to clipboard
| Challenge: | Despite the recent progress for summarization models in producing fluent summaries, they still encounter challenges when long sequences of generated texts and inputs (over thousands of words) need to be evaluated. |
| Approach: | They conduct a systematic analysis of factual-consistency evaluation systems across four long-document datasets and examine the relationship between sentence-level and summary-level model performance. |
| Outcome: | The proposed models can achieve higher recall in error detection for older summaries, yet struggle with false positives and fine-grained error detection. |
Discussion Tracker: Supporting Teacher Learning about Students’ Collaborative Argumentation in High School Classrooms (2020.coling-demos)
Copied to clipboard
| Challenge: | Discussion Tracker provides teachers with data about argument moves, specificity and collaboration . |
| Approach: | They have developed a classroom discussion analytics system that leverages natural language processing to classify argument moves, specificity and collaboration. |
| Outcome: | The proposed system performs with moderate to substantial agreement with humans in a classroom setting. |
From Information to Insight: Leveraging LLMs for Open Aspect-Based Educational Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | a novel dataset summarizes student reflections on STEM lectures . ReflectASP eases the exploration of open-aspect-based summarization (OABS) despite the limitations of current datasets, it is still under-explored. |
| Approach: | They propose a dataset that summarizes student reflections on STEM lectures . they propose two refinement methods to improve summaries . |
| Outcome: | The proposed dataset summarizes student reflections on STEM lectures using automatic and human evaluations. |
Contextual Argument Component Classification for Class Discussions (2020.coling-main)
Copied to clipboard
| Challenge: | Argument mining systems often consider contextual information when training to perform tasks such as argument component identification, classification, and relation extraction. |
| Approach: | They propose to incorporate speaker context and local discourse context into a model for classifying argument components in multi-party classroom discussions. |
| Outcome: | The proposed model improves when varying context size and position . the results support the claim that context size is important . |
ReflectSumm: A Benchmark for Course Reflection Summarization (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing research has focused on standard summarization benchmarks within domains like news, scientific articles, and opinions. |
| Approach: | They propose a summarization dataset specifically designed for summarizing students’ reflective writing. |
| Outcome: | The proposed summarization dataset can be used in opinion summarizing scenarios and in educational domains. |