Steven Bethard

Steven Bethard

Modern neural network libraries all take as a hyperparameter a random seed, typically used to determine the initial state of the model parameters. This opinion piece argues that there are some safe uses for random seeds: as part of the hyperparameter search to select a good model, creating an ensemble of several models, or measuring the sensitivity of the training algorithm to the random seed hyperparameter. It argues that some uses for random seeds are risky: using a fixed random seed for "replicability" and varying only the random seed to create score distributions for performance comparison. An analysis of 85 recent publications from the ACL Anthology finds that more than 50% contain risky uses of random seeds.

Xin Su, Tiep Le, Steven Bethard et al.

An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external unstructured knowledge. Most existing prompting methods either rely on one or two of these sources, or require repeatedly invoking large language models to generate similar or identical content. In this work, we overcome these limitations by introducing a novel semi-structured prompting approach that seamlessly integrates the model's parametric memory with unstructured knowledge from text documents and structured knowledge from knowledge graphs. Experimental results on open-domain multi-hop question answering datasets demonstrate that our prompting method significantly surpasses existing techniques, even exceeding those that require fine-tuning.

Zhengzhong Liang, Tushar Khot, Steven Bethard et al.

Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC). A popular approach to improve the system's performance is to improve the quality of the retrieved context from the IR stage. In this work we show that for StrategyQA, a challenging open-domain QA dataset that requires multi-hop reasoning, this common approach is surprisingly ineffective -- improving the quality of the retrieved context hardly improves the system's performance. We further analyze the system's behavior to identify potential reasons.

Shahriar Golchin, Mihai Surdeanu, Steven Bethard et al.

In-context learning (ICL) has proven to be an effective strategy for improving the performance of large language models (LLMs) with no additional training. However, the exact mechanism behind this performance improvement remains unclear. This study is the first to show how ICL surfaces memorized training data and to explore the correlation between this memorization and performance on downstream tasks across various ICL regimes: zero-shot, few-shot, and many-shot. Our most notable findings include: (1) ICL significantly surfaces memorization compared to zero-shot learning in most cases; (2) demonstrations, without their labels, are the most effective element in surfacing memorization; (3) ICL improves performance when the surfaced memorization in few-shot regimes reaches a high level (about 40%); and (4) there is a very strong correlation between performance and memorization in ICL when it outperforms zero-shot learning. Overall, our study uncovers memorization as a new factor impacting ICL, raising an important question: to what extent do LLMs truly generalize from demonstrations in ICL, and how much of their success is due to memorization?

Xin Su, Phillip Howard, Nagib Hakim et al.

Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely using a provided text document, or whether they can benefit from additional temporal information extracted using other systems. We address this research question by applying existing temporal information extraction systems to construct temporal graphs of events, times, and temporal relations in questions and documents. We then investigate different approaches for fusing these graphs into Transformer models. Experimental results show that our proposed approach for fusing temporal graphs into input text substantially enhances the temporal reasoning capabilities of Transformer models with or without fine-tuning. Additionally, our proposed method outperforms various graph convolution-based approaches and establishes a new state-of-the-art performance on SituatedQA and three splits of TimeQA.

Nazia Tasnim, Md. Istiak Hossain Shihab, Asif Shahriyar Sushmit et al.

Many areas, such as the biological and healthcare domain, artistic works, and organization names, have nested, overlapping, discontinuous entity mentions that may even be syntactically or semantically ambiguous in practice. Traditional sequence tagging algorithms are unable to recognize these complex mentions because they may violate the assumptions upon which sequence tagging schemes are founded. In this paper, we describe our contribution to SemEval 2022 Task 11 on identifying such complex Named Entities. We have leveraged the ensemble of multiple ELECTRA-based models that were exclusively pretrained on the Bangla language with the performance of ELECTRA-based models pretrained on English to achieve competitive performance on the Track-11. Besides providing a system description, we will also present the outcomes of our experiments on architectural decisions, dataset augmentations, and post-competition findings.

Zhengzhong Liang, Zeyu Zhang, Steven Bethard et al.

Languages models have been successfully applied to a variety of reasoning tasks in NLP, yet the language models still suffer from compositional generalization. In this paper we present Explainable Verbal Reasoner Plus (EVR+), a reasoning framework that enhances language models' compositional reasoning ability by (1) allowing the model to explicitly generate and execute symbolic operators, and (2) allowing the model to decompose a complex task into several simpler ones in a flexible manner. Compared with its predecessor Explainable Verbal Reasoner (EVR) and other previous approaches adopting similar ideas, our framework supports more diverse types of reasoning such as nested loops and different types of recursion. To evaluate our reasoning framework, we build a synthetic dataset with five tasks that require compositional reasoning. Results show that our reasoning framework can enhance the language model's compositional generalization performance on the five tasks, using a fine-tuned language model. We also discussed the possibility and the challenges to combine our reasoning framework with a few-shot prompted language model.

Lingyao Li, Deyi Li, Chen Chen et al.

Large language models (LLMs) are increasingly deployed across healthcare applications, including clinical documentation, diagnostic reasoning, medicine recommendation, and medical education. Their outputs are largely unstructured clinical text, which is difficult to reliably evaluate at scale. LLM-as-a-Judge, in which an LLM evaluates another system's output against task-specific criteria, offers a scalable alternative and is increasingly used in clinical evaluation, yet its validity in healthcare remains underexamined. Existing reviews focus on general-purpose LLM evaluation or on risk framework, rather than systematically characterizing how LLM-as-a-Judge is applied in healthcare and how well their judgments align with human experts. We therefore conduct a PRISMA-guided comprehensive review of LLM-as-a-Judge applications in healthcare, searching five databases for studies published between January 2023 and February 2026. After screening 541 records, 134 studies meet the eligibility and are coded by health scenario, judge configuration, technical approach, and validation design. LLM-as-a-Judge is concentrated in clinical decision support, clinical natural language processing (NLP), medical knowledge and question answering (QA), and medical communication. OpenAI models are the most frequently used judges, and prompt engineering appears in nearly all studies, with ensemble, multi-agent, and retrieval-augmented designs as common extensions. Among studies reporting human validation, LLM judges often show moderate to strong alignment with expert judgments, although reliability varies substantially across tasks. Overall, this review positions LLM-as-a-Judge as a promising framework for scalable healthcare AI evaluation, while emphasizing that its clinical value depends on model design and rigorous validation.

Zeyu Zhang, Steven Bethard

Geocoding is the task of converting location mentions in text into structured data that encodes the geospatial semantics. We propose a new architecture for geocoding, GeoNorm. GeoNorm first uses information retrieval techniques to generate a list of candidate entries from the geospatial ontology. Then it reranks the candidate entries using a transformer-based neural network that incorporates information from the ontology such as the entry's population. This generate-and-rerank process is applied twice: first to resolve the less ambiguous countries, states, and counties, and second to resolve the remaining location mentions, using the identified countries, states, and counties as context. Our proposed toponym resolution framework achieves state-of-the-art performance on multiple datasets. Code and models are available at \url{https://github.com/clulab/geonorm}.

Yingya Li, Timothy Miller, Steven Bethard et al.

The success of multi-task learning can depend heavily on which tasks are grouped together. Naively grouping all tasks or a random set of tasks can result in negative transfer, with the multi-task models performing worse than single-task models. Though many efforts have been made to identify task groupings and to measure the relatedness among different tasks, it remains a challenging research topic to define a metric to identify the best task grouping out of a pool of many potential task combinations. We propose a metric of task relatedness based on task difficulty measured by pointwise V-usable information (PVI). PVI is a recently proposed metric to estimate how much usable information a dataset contains given a model. We hypothesize that tasks with not statistically different PVI estimates are similar enough to benefit from the joint learning process. We conduct comprehensive experiments to evaluate the feasibility of this metric for task grouping on 15 NLP datasets in the general, biomedical, and clinical domains. We compare the results of the joint learners against single learners, existing baseline methods, and recent large language models, including Llama 2 and GPT-4. The results show that by grouping tasks with similar PVI estimates, the joint learners yielded competitive results with fewer total parameters, with consistent performance across domains.

Xin Su, Phillip Howard, Steven Bethard

Temporal information extraction (IE) aims to extract structured temporal information from unstructured text, thereby uncovering the implicit timelines within. This technique is applied across domains such as healthcare, newswire, and intelligence analysis, aiding models in these areas to perform temporal reasoning and enabling human users to grasp the temporal structure of text. Transformer-based pre-trained language models have produced revolutionary advancements in natural language processing, demonstrating exceptional performance across a multitude of tasks. Despite the achievements garnered by Transformer-based approaches in temporal IE, there is a lack of comprehensive reviews on these endeavors. In this paper, we aim to bridge this gap by systematically summarizing and analyzing the body of work on temporal IE using Transformers while highlighting potential future research directions.

Xin Su, Sungduk Yu, Phillip Howard et al.

Time normalization is the task of converting natural language temporal expressions into machine-readable representations. It underpins many downstream applications in information retrieval, question answering, and clinical decision-making. Traditional systems based on the ISO-TimeML schema limit expressivity and struggle with complex constructs such as compositional, event-relative, and multi-span time expressions. In this work, we introduce a novel formulation of time normalization as a code generation task grounded in the SCATE framework, which defines temporal semantics through symbolic and compositional operators. We implement a fully executable SCATE Python library and demonstrate that large language models (LLMs) can generate executable SCATE code. Leveraging this capability, we develop an automatic data augmentation pipeline using LLMs to synthesize large-scale annotated data with code-level validation. Our experiments show that small, locally deployable models trained on this augmented data can achieve strong performance, outperforming even their LLM parents and enabling practical, accurate, and interpretable time normalization.

Vikas Yadav, Steven Bethard, Mihai Surdeanu

Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.

Vikas Yadav, Steven Bethard, Mihai Surdeanu

We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. This unsupervised sentence selection method can be coupled with any supervised QA approach. We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2's Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC). We obtain new state-of-the-art performance on both datasets among approaches that do not use external resources for training the QA system: 56.82% F1 on ARC (41.24% on Challenge and 64.49% on Easy) and 26.1% EM0 on MultiRC. Our justification sentences have higher quality than the justifications selected by a strong information retrieval baseline, e.g., by 5.4% F1 in MultiRC. We also show that our unsupervised selection of justification sentences is more stable across domains than a state-of-the-art supervised sentence selection method.

Vikas Yadav, Steven Bethard

Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc. NER systems have been studied and developed widely for decades, but accurate systems using deep neural networks (NN) have only been introduced in the last few years. We present a comprehensive survey of deep neural network architectures for NER, and contrast them with previous approaches to NER based on feature engineering and other supervised or semi-supervised learning algorithms. Our results highlight the improvements achieved by neural networks, and show how incorporating some of the lessons learned from past work on feature-based NER systems can yield further improvements.

Farig Sadeque, Steven Bethard

Since the introduction of social media, user participation or engagement has received little research attention. In this survey article, we establish the notion of participation in social media and main challenges that researchers may face while exploring this phenomenon. We surveyed a handful of research articles that had been done in this area, and tried to extract, analyze and summarize the techniques performed by the researchers. We classified these works based on our task definitions, and explored the machine learning models that have been used for any kind of participation prediction. We also explored the vast amount of features that have been proven useful, and classified them into categories for better understanding and ease of re-implementation. We have found that the success of a technique mostly depends on the type of the network that has been researched on, and there is no universal machine learning algorithm or feature sets that works reasonably well in all types of social media. There is a lack of attempts in implementing state-of-the-art machine learning techniques like neural networks, and the possibility of transfer learning and domain adaptation has not been explored.

Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens

Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse. We introduce an approach to iSRL based on a predictive recurrent neural semantic frame model (PRNSFM) that uses a large unannotated corpus to learn the probability of a sequence of semantic arguments given a predicate. We leverage the sequence probabilities predicted by the PRNSFM to estimate selectional preferences for predicates and their arguments. On the NomBank iSRL test set, our approach improves state-of-the-art performance on implicit semantic role labeling with less reliance than prior work on manually constructed language resources.

Steven Bethard, Leon Derczynski, James Pustejovsky et al.

We describe the Clinical TempEval task which is currently in preparation for the SemEval-2015 evaluation exercise. This task involves identifying and describing events, times and the relations between them in clinical text. Six discrete subtasks are included, focusing on recognising mentions of times and events, describing those mentions for both entity types, identifying the relation between an event and the document creation time, and identifying narrative container relations.