Francis Ferraro

Shubhashis Roy Dipta, Ankur Padia, Francis Ferraro

Claim verification splits between end-to-end classifiers that are accurate but yields no inspectable traces, and decomposition-based methods produce inspectable traces but lag performance on benchmark datasets. We propose DecomposeRL an accurate claim-verifier that produce inspectable traces. DecomposeRL frames decomposition as an RL policy trained with GRPO and a multi-faceted reward ensemble, enabling both fully supervised and semi-supervised learning from unlabeled claims. DecomposeRL addresses the prohibitive training cost of GRPO with a data-curation funnel that distills 115K fact-verification claims into a compact, learning-signal-dense subset of 5K claims. We show that a DecomposeRL-7B policy trained with full supervision on only ~5K curated claims achieves 86.3 in-domain and 69.8 out-of-domain balanced accuracy across 11 claim-verification benchmarks containing biomedical, political, scientific, and general-domain claims. Despite being 4x smaller, it matches 32B baselines and GPT-4.1-mini, and it further outperforms baselines in a semi-supervised setting with only 10% labeled claims data. Code, data, and models are available at https://dipta007.github.io/DecomposeRL

Fred Lu, Ryan R. Curtin, Edward Raff et al.

As the size of datasets used in statistical learning continues to grow, distributed training of models has attracted increasing attention. These methods partition the data and exploit parallelism to reduce memory and runtime, but suffer increasingly from communication costs as the data size or the number of iterations grows. Recent work on linear models has shown that a surrogate likelihood can be optimized locally to iteratively improve on an initial solution in a communication-efficient manner. However, existing versions of these methods experience multiple shortcomings as the data size becomes massive, including diverging updates and efficiently handling sparsity. In this work we develop solutions to these problems which enable us to learn a communication-efficient distributed logistic regression model even beyond millions of features. In our experiments we demonstrate a large improvement in accuracy over distributed algorithms with only a few distributed update steps needed, and similar or faster runtimes. Our code is available at \url{https://github.com/FutureComputing4AI/ProxCSL}.

Yuxuan Jiang, Francis Ferraro

On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision. Although OPD operates on trajectories, its learning signal remains token-level: it identifies deviations through high-loss tokens and repairs them through local reverse-KL correction. We show that this "trajectory-sampled but token-learned" mechanism cannot reliably bridge student trajectories toward teacher trajectories. About 30% of high-loss tokens fall into the low-divergence regime, indicating that many are surface-form mismatches rather than real reasoning forks. Moreover, even truly divergent tokens are difficult to repair with isolated token-level supervision, since reasoning failures often unfold as short-horizon distributional drift. We propose Trajectory-aware OPD (TOPD), which uses near-future trajectory information to identify real divergent states and distribute guidance across multiple future tokens. Experiments show that suppressing non-divergent high-loss tokens improves standard OPD from 47.8% to 48.2% average accuracy, while TOPD further improves performance to 52.2%, with gains on AIME24 from 60.0% to 63.3% and AIME25 from 46.7% to 53.3%.

Fred Lu, Joseph Munoz, Maya Fuchs et al.

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or membership inference, they have been tailored to specific models or have demonstrated low statistical power. Our work develops a general methodology to empirically evaluate the privacy of differentially private machine learning implementations, combining improved privacy search and verification methods with a toolkit of influence-based poisoning attacks. We demonstrate significantly improved auditing power over previous approaches on a variety of models including logistic regression, Naive Bayes, and random forest. Our method can be used to detect privacy violations due to implementation errors or misuse. When violations are not present, it can aid in understanding the amount of information that can be leaked from a given dataset, algorithm, and privacy specification.

Sai Vallurupalli, Sayontan Ghosh, Katrin Erk et al.

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, crowd workers are able to (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 the outcome 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 of 8K short newswire narratives and ROCStories with high inter-annotator agreement (0.74-0.96 weighted Fleiss Kappa). Our dataset, POQue (Participant Outcome Questions), enables the exploration 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.

Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen et al.

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).

Fred Lu, Edward Raff, Francis Ferraro

Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e.g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space. The study of non-Euclidean geometries is often not explored, which we believe is due to a lack of tools for learning non-Euclidean measures of distance. Recent work has shown that Bregman divergences can be learned from data, opening a promising approach to learning asymmetric distances. We propose a new approach to learning arbitrary Bergman divergences in a differentiable manner via input convex neural networks and show that it overcomes significant limitations of previous works. We also demonstrate that our method more faithfully learns divergences over a set of both new and previously studied tasks, including asymmetric regression, ranking, and clustering. Our tests further extend to known asymmetric, but non-Bregman tasks, where our method still performs competitively despite misspecification, showing the general utility of our approach for asymmetric learning.

Mehdi Rezaee, Francis Ferraro

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.

Seyedali Mohammadi, Manas Gaur, Francis Ferraro

Scientific feasibility assessment asks whether a claim is consistent with established knowledge and whether experimental evidence could support or refute it. We frame feasibility assessment as a diagnostic reasoning task in which, given a hypothesis, a model predicts feasible or infeasible and justifies its decision. We evaluate large language models (LLMs) under controlled knowledge conditions (hypothesis-only, with experiments, with outcomes, or both) and probe robustness by progressively removing portions of the experimental and/or outcome context. Across multiple LLMs and two datasets, providing outcome evidence is generally more reliable than providing experiment descriptions. Outcomes tend to improve accuracy beyond what internal knowledge alone provides, whereas experimental text can be brittle and may degrade performance when the context is incomplete. These findings clarify when experimental evidence benefits LLM-based feasibility assessment and when it introduces fragility.

Shubhashis Roy Dipta, Mehdi Rezaee, Francis Ferraro

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 consists of 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.

Sai Vallurupalli, Katrin Erk, Francis Ferraro

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.

Yuxuan Jiang, Francis Ferraro

Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning. While process-level reward models offer a promising direction, existing LLM-based judges often produce noisy and inconsistent signals because they lack fine-grained, task-specific rubrics to distinguish high-level planning from low-level execution. In this work, we introduce SCRIBE (Skill-Conditioned Reward with Intermediate Behavioral Evaluation), a reinforcement learning framework that intervenes at a novel mid-level abstraction. SCRIBE grounds reward modeling in a curated library of skill prototypes, transforming open-ended LLM evaluation into a constrained verification problem. By routing each subgoal to a corresponding prototype, the reward model is equipped with precise, structured rubrics that substantially reduce reward variance. Experimental results show that SCRIBE achieves state-of-the-art performance across a range of reasoning and tool-use benchmarks. In particular, it improves the AIME25 accuracy of a Qwen3-4B model from 43.3% to 63.3%, and significantly increases success rates in complex multi-turn tool interactions. Further analysis of training dynamics reveals a co-evolution across abstraction levels, where mastery of mid-level skills consistently precedes the emergence of effective high-level planning behaviors. Finally, we demonstrate that SCRIBE is additive to low-level tool optimizations, providing a scalable and complementary pathway toward more autonomous and reliable tool-using agents.

Alexander Martin, Reno Kriz, William Gantt Walden et al.

We introduce the task of grounded article generation with the goal of creating a Wikipedia-style article from multiple diverse videos about real-world events -- from natural disasters to political elections -- where all the information in the article is supported by video evidence. Videos are intuitive sources for retrieval-augmented generation (RAG), but most contemporary RAG workflows focus heavily on text while existing methods for video-based summarization focus on low-level scene understanding rather than high-level event semantics. To close this gap, we introduce WikiVideo, a benchmark consisting of expert-written articles and densely annotated videos that provide evidence for articles' claims, facilitating the integration of video into RAG pipelines and enabling the creation of in-depth content that is grounded in multimodal sources. We further propose Collaborative Article Generation (CAG), a novel interactive method for article creation from multiple videos. CAG leverages an iterative interaction between an r1-style reasoning model and a VideoLLM to draw higher-level inferences about the target event than is possible with VideoLLMs alone, which fixate on low-level visual features. We benchmark state-of-the-art VideoLLMs and CAG in both oracle retrieval and RAG settings and find that CAG consistently outperforms alternative methods, while suggesting intriguing avenues for future work.

Yuxuan Jiang, Francis Ferraro

Recently, Large Language Models (LLMs) have shown impressive performance in character understanding tasks, such as analyzing the roles, personalities, and relationships of fictional characters. However, the extensive pre-training corpora used by LLMs raise concerns that they may rely on memorizing popular fictional works rather than genuinely understanding and reasoning about them. In this work, we argue that 'gist memory'-capturing essential meaning - should be the primary mechanism for character understanding tasks, as opposed to 'verbatim memory' - exact match of a string. We introduce a simple yet effective method to mitigate mechanized memorization in character understanding evaluations while preserving the essential implicit cues needed for comprehension and reasoning. Our approach reduces memorization-driven performance on popular fictional works from 96% accuracy to 72% and results in up to an 18% drop in accuracy across various character understanding tasks. These findings underscore the issue of data contamination in existing benchmarks, which often measure memorization rather than true character understanding.

Shubhashis Roy Dipta, Francis Ferraro

Recent approaches have shown impressive proficiency in extracting and leveraging parametric knowledge from Large-Language Models (LLMs) and Vision-Language Models (VLMs). In this work, we consider how we can improve the identification and retrieval of videos related to complex real-world events by automatically extracting latent parametric knowledge about those events. We present Q2E: a Query-to-Event decomposition method for zero-shot multilingual text-to-video retrieval, adaptable across datasets, domains, LLMs, or VLMs. Our approach demonstrates that we can enhance the understanding of otherwise overly simplified human queries by decomposing the query using the knowledge embedded in LLMs and VLMs. We additionally show how to apply our approach to both visual and speech-based inputs. To combine this varied multimodal knowledge, we adopt entropy-based fusion scoring for zero-shot fusion. Through evaluations on two diverse datasets and multiple retrieval metrics, we demonstrate that Q2E outperforms several state-of-the-art baselines. Our evaluation also shows that integrating audio information can significantly improve text-to-video retrieval. We have released code and data for future research.

Siddhant Gupta, Fred Lu, Andrew Barlow et al.

A strategy used by malicious actors is to "live off the land," where benign systems and tools already available on a victim's systems are used and repurposed for the malicious actor's intent. In this work, we ask if there is a way for anti-virus developers to similarly re-purpose existing work to improve their malware detection capability. We show that this is plausible via YARA rules, which use human-written signatures to detect specific malware families, functionalities, or other markers of interest. By extracting sub-signatures from publicly available YARA rules, we assembled a set of features that can more effectively discriminate malicious samples from benign ones. Our experiments demonstrate that these features add value beyond traditional features on the EMBER 2018 dataset. Manual analysis of the added sub-signatures shows a power-law behavior in a combination of features that are specific and unique, as well as features that occur often. A prior expectation may be that the features would be limited in being overly specific to unique malware families. This behavior is observed, and is apparently useful in practice. In addition, we also find sub-signatures that are dual-purpose (e.g., detecting virtual machine environments) or broadly generic (e.g., DLL imports).

Maithili Kadam, Francis Ferraro

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.

Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba et al.

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.

Shubhashis Roy Dipta, Francis Ferraro

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.

Christian M. Angel, Francis Ferraro

The active research topic of prompt engineering makes it evident that LLMs are sensitive to small changes in prompt wording. A portion of this can be ascribed to the inductive bias that is present in the LLM. By using an LLM's output as a portion of its prompt, we can more easily create satisfactory wording for prompts. This has the effect of creating a prompt that matches the inductive bias in model. Empirically, we show that using this Inductive Bias Extraction and Matching strategy improves LLM Likert ratings used for classification by up to 19% and LLM Likert ratings used for ranking by up to 27%.

Sai Vallurupalli, Francis Ferraro

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.

Mollie Shichman, Claire Bonial, Austin Blodgett et al.

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.

Seyedali Mohammadi, Edward Raff, Jinendra Malekar et al.

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.

Fred Lu, Ryan R. Curtin, Edward Raff et al.

While distributed training is often viewed as a solution to optimizing linear models on increasingly large datasets, inter-machine communication costs of popular distributed approaches can dominate as data dimensionality increases. Recent work on non-interactive algorithms shows that approximate solutions for linear models can be obtained efficiently with only a single round of communication among machines. However, this approximation often degenerates as the number of machines increases. In this paper, building on the recent optimal weighted average method, we introduce a new technique, ACOWA, that allows an extra round of communication to achieve noticeably better approximation quality with minor runtime increases. Results show that for sparse distributed logistic regression, ACOWA obtains solutions that are more faithful to the empirical risk minimizer and attain substantially higher accuracy than other distributed algorithms.

Ishani Mondal, Michelle Yuan, Anandhavelu N et al.

Learning template based information extraction from documents is a crucial yet difficult task. Prior template-based IE approaches assume foreknowledge of the domain templates; however, real-world IE do not have pre-defined schemas and it is a figure-out-as you go phenomena. To quickly bootstrap templates in a real-world setting, we need to induce template slots from documents with zero or minimal supervision. Since the purpose of question answering intersect with the goal of information extraction, we use automatic question generation to induce template slots from the documents and investigate how a tiny amount of a proxy human-supervision on-the-fly (termed as InteractiveIE) can further boost the performance. Extensive experiments on biomedical and legal documents, where obtaining training data is expensive, reveal encouraging trends of performance improvement using InteractiveIE over AI-only baseline.

Fred Lu, Francis Ferraro, Edward Raff

Ordinal regression is a classification task where classes have an order and prediction error increases the further the predicted class is from the true class. The standard approach for modeling ordinal data involves fitting parallel separating hyperplanes that optimize a certain loss function. This assumption offers sample efficient learning via inductive bias, but is often too restrictive in real-world datasets where features may have varying effects across different categories. Allowing class-specific hyperplane slopes creates generalized logistic ordinal regression, increasing the flexibility of the model at a cost to sample efficiency. We explore an extension of the generalized model to the all-thresholds logistic loss and propose a regularization approach that interpolates between these two extremes. Our method, which we term continuously generalized ordinal logistic, significantly outperforms the standard ordinal logistic model over a thorough set of ordinal regression benchmark datasets. We further extend this method to deep learning and show that it achieves competitive or lower prediction error compared to previous models over a range of datasets and modalities. Furthermore, two primary alternative models for deep learning ordinal regression are shown to be special cases of our framework.

Gaoussou Youssouf Kebe, Luke E. Richards, Edward Raff et al.

Learning to understand grounded language, which connects natural language to percepts, is a critical research area. Prior work in grounded language acquisition has focused primarily on textual inputs. In this work we demonstrate the feasibility of performing grounded language acquisition on paired visual percepts and raw speech inputs. This will allow interactions in which language about novel tasks and environments is learned from end users, reducing dependence on textual inputs and potentially mitigating the effects of demographic bias found in widely available speech recognition systems. We leverage recent work in self-supervised speech representation models and show that learned representations of speech can make language grounding systems more inclusive towards specific groups while maintaining or even increasing general performance.

Mohammad Umair, Francis Ferraro

We introduce semantic form mid-tuning, an approach for transferring semantic knowledge from semantic meaning representations into transformer-based language encoders. In mid-tuning, we learn to align the text of general sentences -- not tied to any particular inference task -- and structured semantic representations of those sentences. Our approach does not require gold annotated semantic representations. Instead, it makes use of automatically generated semantic representations, such as from off-the-shelf PropBank and FrameNet semantic parsers. We show that this alignment can be learned implicitly via classification or directly via triplet loss. Our method yields language encoders that demonstrate improved predictive performance across inference, reading comprehension, textual similarity, and other semantic tasks drawn from the GLUE, SuperGLUE, and SentEval benchmarks. We evaluate our approach on three popular baseline models, where our experimental results and analysis concludes that current pre-trained language models can further benefit from structured semantic frames with the proposed mid-tuning method, as they inject additional task-agnostic knowledge to the encoder, improving the generated embeddings as well as the linguistic properties of the given model, as evident from improvements on a popular sentence embedding toolkit and a variety of probing tasks.

Mehdi Rezaee, Kasra Darvish, Gaoussou Youssouf Kebe et al.

We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to generate the text and learn a SE classifier. Test set and cross-genre evaluations show that when training data is plentiful, the proposed model can improve over the previous discriminative state-of-the-art models. Our approach performs disproportionately better with smaller amounts of training data, but when faced with extremely small sets (4 instances per label), generative RNN methods outperform transformers. Our work provides guidance for future efforts on SE and semantic prediction tasks, and low-label training regimes.

Nisha Pillai, Cynthia Matuszek, Francis Ferraro

We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning of language about a wide range of real-world objects. We evaluate the efficacy of this learning by predicting the semantics of objects and comparing the performance with neural and non-neural inputs. We show that this generative approach exhibits promising results in language grounding without pre-specifying visual categories under low resource settings. Our experiments demonstrate that this approach is generalizable to multilingual, highly varied datasets.

Ashwinkumar Ganesan, Francis Ferraro, Tim Oates

We propose a Bi-Directional Manifold Alignment (BDMA) that learns a non-linear mapping between two manifolds by explicitly training it to be bijective. We demonstrate BDMA by training a model for a pair of languages rather than individual, directed source and target combinations, reducing the number of models by 50%. We show that models trained with BDMA in the "forward" (source to target) direction can successfully map words in the "reverse" (target to source) direction, yielding equivalent (or better) performance to standard unidirectional translation models where the source and target language is flipped. We also show how BDMA reduces the overall size of the model.

Nisha Pillai, Edward Raff, Francis Ferraro et al.

Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning approaches applied to three grounded language problems of varying complexity in order to analyze what methods are suitable for improving data efficiency in learning. We present a method for analyzing the complexity of data in this joint problem space, and report on how characteristics of the underlying task, along with design decisions such as feature selection and classification model, drive the results. We observe that representativeness, along with diversity, is crucial in selecting data samples.

Mehdi Rezaee, Francis Ferraro

We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not rely on stochastic backpropagation to handle the discrete variables. The model we utilize combines the expressive power of neural methods for representing sequences of text with the topic model's ability to capture global, thematic coherence. Using neural variational inference, we show improved perplexity and document understanding across multiple corpora. We examine the effect of prior parameters both on the model and variational parameters and demonstrate how our approach can compete and surpass a popular topic model implementation on an automatic measure of topic quality.

Rajat Patel, Francis Ferraro

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.

Mehdi Rezaee, Francis Ferraro

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.

Patrick Jenkins, Rishabh Sachdeva, Gaoussou Youssouf Kebe et al.

Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI. In practice the data used for learning consists almost entirely of textual descriptions, which tend to be cleaner, clearer, and more grammatical than actual human interactions. In this work, we present the Grounded Language Dataset (GoLD), a multimodal dataset of common household objects described by people using either spoken or written language. We analyze the differences and present an experiment showing how the different modalities affect language learning from human in-put. This will enable researchers studying the intersection of robotics, NLP, and HCI to better investigate how the multiple modalities of image, text, and speech interact, as well as show differences in the vernacular of these modalities impact results.

Ashwinkumar Ganesan, Francis Ferraro, Tim Oates

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 cross-lingual 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.

Aaron Steven White, Elias Stengel-Eskin, Siddharth Vashishtha et al.

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.

Ankur Padia, Kostantinos Kalpakis, Francis Ferraro et al.

We present a family of novel methods for embedding knowledge graphs into real-valued tensors. These tensor-based embeddings capture the ordered relations that are typical in the knowledge graphs represented by semantic web languages like RDF. Unlike many previous models, our methods can easily use prior background knowledge provided by users or extracted automatically from existing knowledge graphs. In addition to providing more robust methods for knowledge graph embedding, we provide a provably-convergent, linear tensor factorization algorithm. We demonstrate the efficacy of our models for the task of predicting new facts across eight different knowledge graphs, achieving between 5% and 50% relative improvement over existing state-of-the-art knowledge graph embedding techniques. Our empirical evaluation shows that all of the tensor decomposition models perform well when the average degree of an entity in a graph is high, with constraint-based models doing better on graphs with a small number of highly similar relations and regularization-based models dominating for graphs with relations of varying degrees of similarity.

Ankur Padia, Francis Ferraro, Tim Finin

Judging the veracity of a sentence making one or more claims is an important and challenging problem with many dimensions. The recent FEVER task asked participants to classify input sentences as either SUPPORTED, REFUTED or NotEnoughInfo using Wikipedia as a source of true facts. SURFACE does this task and explains its decision through a selection of sentences from the trusted source. Our multi-task neural approach uses semantic lexical frames from FrameNet to jointly (i) find relevant evidential sentences in the trusted source and (ii) use them to classify the input sentence's veracity. An evaluation of our efficient three-parameter model on the FEVER dataset showed an improvement of 90% over the state-of-the-art baseline on retrieving relevant sentences and a 70% relative improvement in classification.

Ankur Padia, Francis Ferraro, Tim Finin

KGCleaner is a framework to identify and correct errors in data produced and delivered by an information extraction system. These tasks have been understudied and KGCleaner is the first to address both. We introduce a multi-task model that jointly learns to predict if an extracted relation is credible and repair it if not. We evaluate our approach and other models as instance of our framework on two collections: a Wikidata corpus of nearly 700K facts and 5M fact-relevant sentences and a collection of 30K facts from the 2015 TAC Knowledge Base Population task. For credibility classification, parameter efficient simple shallow neural network can achieve an absolute performance gain of 30 $F_1$ points on Wikidata and comparable performance on TAC. For the repair task, significant performance (at more than twice) gain can be obtained depending on the nature of the dataset and the models.

Francis Ferraro, Adam Poliak, Ryan Cotterell et al.

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.

Ting-Hao, Huang, Francis Ferraro et al.

We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.

Francis Ferraro, Nasrin Mostafazadeh, Ting-Hao et al.

Integrating vision and language has long been a dream in work on artificial intelligence (AI). In the past two years, we have witnessed an explosion of work that brings together vision and language from images to videos and beyond. The available corpora have played a crucial role in advancing this area of research. In this paper, we propose a set of quality metrics for evaluating and analyzing the vision & language datasets and categorize them accordingly. Our analyses show that the most recent datasets have been using more complex language and more abstract concepts, however, there are different strengths and weaknesses in each.