Diane Litman

Large Language Models (LLMs) have shown extraordinary success across various text generation tasks; however, their potential for simple yet essential text classification remains underexplored, as LLM pre-training tends to emphasize generation over classification. While LLMs with instruction tuning can transform classification into a generation task, they often struggle to categorize nuanced texts. One such example is text revision, which involves nuanced edits between pairs of texts. Although simply fine-tuning LLMs for revision classification seems plausible, it requires a large amount of revision annotations, which are exceptionally expensive and scarce in the community. To address this issue, we introduce a plug-and-play layer-wise parameter-efficient fine-tuning (PEFT) framework, i.e., IR-Tuning, which fine-tunes a subset of important LLM layers that are dynamically selected based on their gradient norm distribution, while freezing those of redundant layers. Extensive experiments suggest that IR-Tuning surpasses several layer-wise PEFT baselines over diverse text revisions, while achieving fast convergence, low GPU memory consumption, and effectiveness on small revision corpora.

Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows improved performance on top of different model baselines over several evaluation benchmarks, covering rich domains of texts, focusing on long document summarization. This underscores the significance of incorporating discourse features in developing models for scoring summaries for long document factual inconsistency.

Zhexiong Liu, Diane Litman. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

Yuya Asano, Diane Litman, Erin Walker. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Yang Zhong, Diane Litman. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Mohamed Elaraby, Diane Litman. Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025). 2025.

Nhat Tran, Diane Litman, Benjamin Pierce, Richard Correnti, Lindsay Clare Matsumura. Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025). 2025.

Yang Zhong, Diane Litman. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

Yang Zhong, Diane Litman. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.