Information extraction (IE) needs vary over time, where a flexible information extraction (IE) system can be useful. Despite this, existing IE systems are either fully supervised, requiring expensive human annotations, or fully unsupervised, extracting information that often do not cater to user’s needs. To address these issues, we formally introduce the task of “IE on-the-fly”, and address the problem using our proposed Adaptive IE framework that uses human-in-the-loop refinement to adapt to changing user questions. Through human experiments on three diverse datasets, we demonstrate that Adaptive IE is a domain-agnostic, responsive, efficient framework for helping users access useful information while quickly reorganizing information in response to evolving information needs.

Do LLMs genuinely incorporate external definitions, or do they primarily rely on their parametric knowledge? To address these questions, we conduct controlled experiments across multiple explanation benchmark datasets (general and domain-specific) and label definition conditions, including expert-curated, LLM-generated, perturbed, and swapped definitions. Our results reveal that while explicit label definitions can enhance accuracy and explainability, their integration into an LLM’s task-solving processes is neither guaranteed nor consistent, suggesting reliance on internalized representations in many cases. Models often default to their internal representations, particularly in general tasks, whereas domain-specific tasks benefit more from explicit definitions. These findings underscore the need for a deeper understanding of how LLMs process external knowledge alongside their pre-existing capabilities.

Knowing which latent conditions lead to a particular outcome is useful for critically examining claims made about complex event outcomes. Identifying implied conditions and examining their influence on an outcome is challenging. We handle this by combining and augmenting annotations from two existing datasets consisting of goals and states, and explore the influence of conditions through our research questions and Condition-based Reasoning tasks. We examine open and closed LLMs of varying sizes and intent-alignment on our reasoning tasks and find that conditions are useful when not all context is available. Models differ widely in their ability to generate and identify outcome-variant conditions, which affects their performance on outcome validation, when conditions are used to replace missing context. Larger models like GPT-4o, are more cautious in such less constrained situations.

During Human Robot Interactions in disaster relief scenarios, Large Language Models (LLMs) have the potential for substantial physical reasoning to assist in mission objectives. However, these reasoning capabilities are often found only in larger models, which are not currently reasonable to deploy on robotic systems due to size constraints. To meet our problem space requirements, we introduce a dataset and pipeline to create Field Reasoning and Instruction Decoding Agent (FRIDA) models. In our pipeline, domain experts and linguists combine their knowledge to make high-quality, few-shot prompts used to generate synthetic data for fine-tuning. We hand-curate datasets for this few-shot prompting and for evaluation to improve LLM reasoning on both general and disaster-specific objects. We concurrently run an ablation study to understand which kinds of synthetic data most affect performance. We fine-tune several small instruction-tuned models and find that ablated FRIDA models only trained on objects’ physical state and function data outperformed both the FRIDA models trained on all synthetic data and the base models in our evaluation. We demonstrate that the FRIDA pipeline is capable of instilling physical common sense with minimal data.

Prior work has shown that presupposition in generated questions can introduce unverified assumptions, leading to inconsistencies in claim verification. Additionally, prompt sensitivity remains a significant challenge for large language models (LLMs), resulting in performance variance as high as **3–6%**. While recent advancements have reduced this gap, our study demonstrates that prompt sensitivity remains a persistent issue. To address this, we propose a structured and robust claim verification framework that reasons through presupposition-free, decomposed questions. Extensive experiments across multiple prompts, datasets, and LLMs reveal that even state-of-the-art models remain susceptible to prompt variance and presupposition. Our method consistently mitigates these issues, achieving up to a **2–5%** improvement.

Large language models (LLMs) excel at general language tasks but often struggle with event-based questions—especially those requiring causal or temporal reasoning. We introduce TAG-EQA (Text-And-Graph for Event Question Answering), a prompting framework that injects causal event graphs into LLM inputs by converting structured relations into natural-language statements. TAG-EQA spans nine prompting configurations, combining three strategies (zero-shot, few-shot, chain-of-thought) with three input modalities (text-only, graph-only, text+graph), enabling a systematic analysis of when and how structured knowledge aids inference. On the TORQUESTRA benchmark, TAG-EQA improves accuracy by ~5% on average over text-only baselines, with gains up to ~12% in zero-shot settings and ~18% when graph-augmented CoT prompting is effective. While performance varies by model and configuration, our findings show that causal graphs can enhance event reasoning in LLMs without fine-tuning, offering a flexible way to encode structure in prompt-based QA.

Language Models (LMs) are being proposed for mental health applications where the heightened risk of adverse outcomes means predictive performance may not be a sufficient litmus test of a model’s utility in clinical practice. A model that can be trusted for practice should have a correspondence between explanation and clinical determination, yet no prior research has examined the attention fidelity of these models and their effect on ground truth explanations. We introduce an evaluation design that focuses on the robustness and explainability of LMs in identifying Wellness Dimensions (WDs). We focus on two existing mental health and well-being datasets: (a) Multi-label Classification-based MultiWD, and (b) WellXplain for evaluating attention mechanism veracity against expert-labeled explanations. The labels are based on Halbert Dunn’s theory of wellness, which gives grounding to our evaluation. We reveal four surprising results about LMs/LLMs: (1) Despite their human-like capabilities, GPT-3.5/4 lag behind RoBERTa, and MedAlpaca, a fine-tuned LLM on WellXplain fails to deliver any remarkable improvements in performance or explanations. (2) Re-examining LMs’ predictions based on a confidence-oriented loss function reveals a significant performance drop. (3) Across all LMs/LLMs, the alignment between attention and explanations remains low, with LLMs scoring a dismal 0.0. (4) Most mental health-specific LMs/LLMs overlook domain-specific knowledge and undervalue explanations, causing these discrepancies. This study highlights the need for further research into their consistency and explanations in mental health and well-being.

For human-robot dialogue in a search-and-rescue scenario, a strong knowledge of the conditions and objects a robot will face is essential for effective interpretation of natural language instructions. In order to utilize the power of large language models without overwhelming the limited storage capacity of a robot, we propose PropBank-Powered Data Creation. PropBank-Powered Data Creation is an expert-in-the-loop data generation pipeline which creates training data for disaster-specific language models. We leverage semantic role labeling and Rich Event Ontology resources to efficiently develop seed sentences for fine-tuning a smaller, targeted model that could operate onboard a robot for disaster relief. We developed 32 sentence templates, which we used to make 2 seed datasets of 175 instructions for earthquake search and rescue and train derailment response. We further leverage our seed datasets as evaluation data to test our baseline fine-tuned models.

Interpreting and assessing goal driven actions is vital to understanding and reasoning over complex events. It is important to be able to acquire the knowledge needed for this understanding, though doing so is challenging. We argue that such knowledge can be elicited through a participant achievement lens. We analyze a complex event in a narrative according to the intended achievements of the participants in that narrative, the likely future actions of the participants, and the likelihood of goal success. We collect 6.3K high quality goal and action annotations reflecting our proposed participant achievement lens, with an average weighted Fleiss-Kappa IAA of 80%. Our collection contains annotated alternate versions of each narrative. These alternate versions vary minimally from the “original” story, but can license drastically different inferences. Our findings suggest that while modern large language models can reflect some of the goal-based knowledge we study, they find it challenging to fully capture the design and intent behind concerted actions, even when the model pretraining included the data from which we extracted the goal knowledge. We show that smaller models fine-tuned on our dataset can achieve performance surpassing larger models.

enter abstract here

The existence of external (“side”) semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information bottleneck-based discrete latent variable model. We reparameterize the model’s discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. Our model is learned to minimize the mutual information between the observed data and optional side knowledge that is not already captured by the new, auxiliary variables. We theoretically show that our approach generalizes past approaches, and perform an empirical case study of our approach on event modeling. We corroborate our theoretical results with strong empirical experiments, showing that the proposed method outperforms previous proposed approaches on multiple datasets.

Schema induction involves creating a graph representation depicting how events unfold in a scenario. We present SAGEViz, an intuitive and modular tool that utilizes human-AI collaboration to create and update complex schema graphs efficiently, where multiple annotators (humans and models) can work simultaneously on a schema graph from any domain. The tool consists of two components: (1) a curation component powered by plug-and-play event language models to create and expand event sequences while human annotators validate and enrich the sequences to build complex hierarchical schemas, and (2) an easy-to-use visualization component to visualize schemas at varying levels of hierarchy. Using supervised and few-shot approaches, our event language models can continually predict relevant events starting from a seed event. We conduct a user study and show that users need less effort in terms of interaction steps with SAGEViz to generate schemas of better quality. We also include a video demonstrating the system.

Language models have shown great promise in common-sense related tasks. However, it remains unseen how they would perform in the context of physically situated human-robot interactions, particularly in disaster-relief sce- narios. In this paper, we develop a language model evaluation dataset with more than 800 cloze sentences, written to probe for the func- tion of over 200 objects. The sentences are divided into two tasks: an “easy” task where the language model has to choose between vo- cabulary with different functions (Task 1), and a “challenge” where it has to choose between vocabulary with the same function, yet only one vocabulary item is appropriate given real world constraints on functionality (Task 2). Dis- tilBERT performs with about 80% accuracy for both tasks. To investigate how annotator variability affected those results, we developed a follow-on experiment where we compared our original results with wrong answers chosen based on embedding vector distances. Those results showed increased precision across docu- ments but a 15% decrease in accuracy. We con- clude that language models do have a strong knowledge basis for object reasoning, but will require creative fine-tuning strategies in order to be successfully deployed.

Prior work has shown that coupling sequential latent variable models with semantic ontological knowledge can improve the representational capabilities of event modeling approaches. In this work, we present a novel, doubly hierarchical, semi-supervised event modeling framework that provides structural hierarchy while also accounting for ontological hierarchy. Our approach consistsof multiple layers of structured latent variables, where each successive layer compresses and abstracts the previous layers. We guide this compression through the injection of structured ontological knowledge that is defined at the type level of events: importantly, our model allows for partial injection of semantic knowledge and it does not depend on observing instances at any particular level of the semantic ontology. Across two different datasets and four different evaluation metrics, we demonstrate that our approach is able to out-perform the previous state-of-the-art approaches by up to 8.5%, demonstrating the benefits of structured and semantic hierarchical knowledge for event modeling.

The events in a narrative are understood as a coherent whole via the underlying states of their participants. Often, these participant states are not explicitly mentioned, instead left to be inferred by the reader. A model that understands narratives should likewise infer these implicit states, and even reason about the impact of changes to these states on the narrative. To facilitate this goal, we introduce a new crowdsourced English-language, Participant States dataset, PASTA. This dataset contains inferable participant states; a counterfactual perturbation to each state; and the changes to the story that would be necessary if the counterfactual were true. We introduce three state-based reasoning tasks that test for the ability to infer when a state is entailed by a story, to revise a story conditioned on a counterfactual state, and to explain the most likely state change given a revised story. Experiments show that today’s LLMs can reason about states to some degree, but there is large room for improvement, especially in problems requiring access and ability to reason with diverse types of knowledge (e.g., physical, numerical, factual).1

Information extraction systems analyze text to produce entities and beliefs, but their output often has errors. In this paper, we analyze the reading consistency of the extracted facts with respect to the text from which they were derived and show how to detect and correct errors. We consider both the scenario when the provenance text is automatically found by an information extraction system and when it is curated by humans. We contrast consistency with credibility; define and explore consistency and repair tasks; and demonstrate a simple yet effective and generalizable model. We analyze these tasks and evaluate this approach on three datasets. Against a strong baseline model, we consistently improve both consistency and repair across three datasets using a simple MLP model with attention and lexical features.

Knowledge about outcomes is critical for complex event understanding but is hard to acquire.We show that by pre-identifying a participant in a complex event, crowdworkers are ableto (1) infer the collective impact of salient events that make up the situation, (2) annotate the volitional engagement of participants in causing the situation, and (3) ground theoutcome of the situation in state changes of the participants. By creating a multi-step interface and a careful quality control strategy, we collect a high quality annotated dataset of8K short newswire narratives and ROCStories with high inter-annotator agreement (0.74-0.96weighted Fleiss Kappa). Our dataset, POQUe (Participant Outcome Questions), enables theexploration and development of models that address multiple aspects of semantic understanding. Experimentally, we show that current language models lag behind human performance in subtle ways through our task formulations that target abstract and specific comprehension of a complex event, its outcome, and a participant’s influence over the event culmination.

We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations. Given two pretrained embedding manifolds, LPL optimizes a model to project an embedding and maintain its local neighborhood while aligning one manifold to another. This reduces the overall size of the dataset required to align the two in tasks such as crosslingual word alignment. We show that the LPL-based alignment between input vector spaces acts as a regularizer, leading to better and consistent accuracy than the baseline, especially when the size of the training set is small. We demonstrate the effectiveness of LPL-optimized alignment on semantic text similarity (STS), natural language inference (SNLI), multi-genre language inference (MNLI) and cross-lingual word alignment (CLA) showing consistent improvements, finding up to 16% improvement over our baseline in lower resource settings.

Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge into account. We construct a sequential neural variational autoencoder, which uses Gumbel-Softmax reparametrization within a carefully defined encoder, to allow for successful backpropagation during training. The core idea is to allow semi-supervised external discrete knowledge to guide, but not restrict, the variational latent parameters during training. Our experiments indicate that our approach not only outperforms multiple baselines and the state-of-the-art in narrative script induction, but also converges more quickly.

We demonstrate the complementary natures of neural knowledge graph embedding, fine-grain entity type prediction, and neural language modeling. We show that a language model-inspired knowledge graph embedding approach yields both improved knowledge graph embeddings and fine-grain entity type representations. Our work also shows that jointly modeling both structured knowledge tuples and language improves both.

We present the Universal Decompositional Semantics (UDS) dataset (v1.0), which is bundled with the Decomp toolkit (v0.1). UDS1.0 unifies five high-quality, decompositional semantics-aligned annotation sets within a single semantic graph specification—with graph structures defined by the predicative patterns produced by the PredPatt tool and real-valued node and edge attributes constructed using sophisticated normalization procedures. The Decomp toolkit provides a suite of Python 3 tools for querying UDS graphs using SPARQL. Both UDS1.0 and Decomp0.1 are publicly available at http://decomp.io.

In this paper we describe a multilingual grounded language learning system adapted from an English-only system. This system learns the meaning of words used in crowd-sourced descriptions by grounding them in the physical representations of the objects they are describing. Our work presents a framework to compare the performance of the system when applied to a new language and to identify modifications necessary to attain equal performance, with the goal of enhancing the ability of robots to learn language from a more diverse range of people. We then demonstrate this system with Spanish, through first analyzing the performance of translated Spanish, and then extending this analysis to a new corpus of crowd-sourced Spanish language data. We find that with small modifications, the system is able to learn color, object, and shape words with comparable performance between languages.

We describe the systems developed by the UMBC team for 2018 SemEval Task 8, SecureNLP (Semantic Extraction from CybersecUrity REports using Natural Language Processing). We participated in three of the sub-tasks: (1) classifying sentences as being relevant or irrelevant to malware, (2) predicting token labels for sentences, and (4) predicting attribute labels from the Malware Attribute Enumeration and Characterization vocabulary for defining malware characteristics. We achieve F1 score of 50.34/18.0 (dev/test), 22.23 (test-data), and 31.98 (test-data) for Task1, Task2 and Task2 respectively. We also make our cybersecurity embeddings publicly available at http://bit.ly/cyber2vec.

We describe our system used in the 2018 FEVER shared task. The system employed a frame-based information retrieval approach to select Wikipedia sentences providing evidence and used a two-layer multilayer perceptron to classify a claim as correct or not. Our submission achieved a score of 0.3966 on the Evidence F1 metric with accuracy of 44.79%, and FEVER score of 0.2628 F1 points.

We study how different frame annotations complement one another when learning continuous lexical semantics. We learn the representations from a tensorized skip-gram model that consistently encodes syntactic-semantic content better, with multiple 10% gains over baselines.

We present the first large-scale, corpus based verification of Dowty’s seminal theory of proto-roles. Our results demonstrate both the need for and the feasibility of a property-based annotation scheme of semantic relationships, as opposed to the currently dominant notion of categorical roles.