Generating plain biomedical summaries with Large Language Models (LLMs) can enhance the accessibility of biomedical knowledge to the public. However, how faithful the generated summaries are remains an open yet critical question. To address this, we propose FaReBio, a benchmark dataset with expert-annotated Faithfulness and Reasoning on plain Biomedical Summaries. This dataset consists of 175 plain summaries ($,445 sentences) generated by seven different LLMs, paired with source articles. Using our dataset, we identify the performance gap of LLMs in generating faithful plain biomedical summaries and observe a negative correlation between abstractiveness and faithfulness. We also show that current faithfulness evaluation metrics do not work well in the biomedical domain and confirm the over-confident tendency of LLMs as faithfulness evaluators. To better understand the faithfulness judgements, we further benchmark LLMs in retrieving supporting evidence and show the gap of LLMs in reasoning faithfulness evaluation at different abstractiveness levels. Going beyond the binary faithfulness labels, coupled with the annotation of supporting sentences, our dataset could further contribute to the understanding of faithfulness evaluation and reasoning.

Effective summarisation evaluation metrics enable researchers and practitioners to compare different summarisation systems efficiently. Estimating the effectiveness of an automatic evaluation metric, termed meta-evaluation, is a critically important research question. In this position paper, we review recent meta-evaluation practices for summarisation evaluation metrics and find that (1) evaluation metrics are primarily meta-evaluated on datasets consisting of examples from news summarisation datasets, and (2) there has been a noticeable shift in research focus towards evaluating the faithfulness of generated summaries. We argue that the time is ripe to build more diverse benchmarks that enable the development of more robust evaluation metrics and analyze the generalization ability of existing evaluation metrics. In addition, we call for research focusing on user-centric quality dimensions that consider the generated summary’s communicative goal and the role of summarisation in the workflow.

How do personal attributes affect biography generation? Addressing this question requires an identical pair of biographies where only the personal attributes of interest are different. However, it is rare in the real world. To address this, we propose a counterfactual methodology from a data-to-text perspective, manipulating the personal attributes of interest while keeping the co-occurring attributes unchanged. We first validate that the fine-tuned Flan-T5 model generates the biographies based on the given attributes. This work expands the analysis of gender-centered bias in text generation. Our results confirm the well-known bias in gender and also show the bias in regions, in both individual and its related co-occurring attributes in semantic machining and sentiment.

Understanding the prevalence and dynamics of justice partisanship and ideology in the US Supreme Court is critical in studying jurisdiction. Most research quantifies partisanship based on voting behavior, and oral arguments in the courtroom — the last essential procedure before the final case outcome — have not been well studied for this purpose. To address this gap, we present a framework for analyzing the language of justices in the courtroom for partisan signals, and study how partisanship in speech aligns with voting patterns. Our results show that the affiliated party of justices can be predicted reliably from their oral contributions. We further show a strong correlation between language partisanship and voting ideology.

Given the complexity of the judiciary in the US Supreme Court, various procedures, along with various resources, contribute to the court system. However, most research focuses on a limited set of resources, e.g., court opinions or oral arguments, for analyzing a specific perspective in court, e.g., partisanship or voting. To gain a fuller understanding of these perspectives in the legal system of the US Supreme Court, a more comprehensive dataset, connecting different sources in different phases of the court procedure, is needed. To address this gap, we present a multi-sourced dataset for the Supreme Court, comprising court resources from different procedural phases, connecting language documents with extensive metadata. We showcase its utility through a case study on how different court documents reveal the decision direction (conservative vs. liberal) of the cases. We analyze performance differences across three protected attributes, indicating that different court resources encode different biases, and reinforcing that considering various resources provides a fuller picture of the court procedures. We further discuss how our dataset can contribute to future research directions.

Procedural text contains rich anaphoric phenomena, yet has not received much attention in NLP. To fill this gap, we investigate the textual properties of two types of procedural text, recipes and chemical patents, and generalize an anaphora annotation framework developed for the chemical domain for modeling anaphoric phenomena in recipes. We apply this framework to annotate the RecipeRef corpus with both bridging and coreference relations. Through comparison to chemical patents, we show the complexity of anaphora resolution in recipes. We demonstrate empirically that transfer learning from the chemical domain improves resolution of anaphora in recipes, suggesting transferability of general procedural knowledge.

In this paper, we investigate the utility of modern pretrained language models for the evidence grading system in the medical literature based on the ALTA 2021 shared task. We benchmark 1) domain-specific models that are optimized for medical literature and 2) domain-generic models with rich latent discourse representation (i.e. ELECTRA, RoBERTa). Our empirical experiments reveal that these modern pretrained language models suffer from high variance, and the ensemble method can improve the model performance. We found that ELECTRA performs best with an accuracy of 53.6% on the test set, outperforming domain-specific models.1

Chemical patents contain rich coreference and bridging links, which are the target of this research. Specially, we introduce a novel annotation scheme, based on which we create the ChEMU-Ref dataset from reaction description snippets in English-language chemical patents. We propose a neural approach to anaphora resolution, which we show to achieve strong results, especially when jointly trained over coreference and bridging links.