Papers by Francis Ferraro
Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing models that perform unidirectional mappings are unipolar and unintended . |
| Approach: | They propose a bi-directional mapping algorithm that learns a non-linear mapping between two manifolds by explicitly training it to be bijective. |
| Outcome: | The proposed model reduces the number of models by 50% and improves performance over unidirectional translation models. |
RevUp: Revise and Update Information Bottleneck for Event Representation (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing external (“side”) semantic knowledge has been shown to result in more expressive computational event models. |
| Approach: | They propose a semi-supervised information bottleneck-based discrete latent variable model that reparameterizes discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. |
| Outcome: | The proposed model outperforms existing models on multiple datasets. |
Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models (2026.acl-short)
Copied to clipboard
| Challenge: | Scientific feasibility assessment asks whether a claim aligns with established knowledge and whether experimental evidence could support or refute it. |
| Approach: | They frame scientific feasibility assessment as a diagnostic reasoning task . given a hypothesis, a model predicts feasible or infeasible and justifies its decision . they evaluate large language models under controlled knowledge conditions . |
| Outcome: | The results show that providing outcome evidence is more reliable than providing experiment descriptions. |
Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions (2025.emnlp-main)
Copied to clipboard
Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba, Edward Raff, Ponnurangam Kumaraguru, Francis Ferraro, Manas Gaur
| Challenge: | Exact label definitions are considered as clues to disambiguate unclear labels, helping models perform their tasks more effectively. |
| Approach: | They conducted controlled experiments on multiple explanation benchmark datasets and label definition conditions using expert-curated, LLM-generated, perturbed, and swapped definitions. |
| Outcome: | The results suggest that models often default to internal representations, particularly in general tasks, while domain-specific tasks benefit more from explicit definitions. |
CoRE: Condition-based Reasoning for Identifying Outcome Variance in Complex Events (2025.findings-acl)
Copied to clipboard
| Challenge: | Identifying implied conditions and examining their influence on an outcome is challenging. |
| Approach: | They combine annotations from goals and states to examine the influence of conditions . they examine open and closed LLMs of varying sizes and intent-alignment on reasoning tasks . |
| Outcome: | The proposed models are more cautious in less constrained situations when conditions are used to replace missing context. |
PASTA: A Dataset for Modeling PArticipant STAtes in Narratives (2023.tacl-1)
Copied to clipboard
Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen, Francis Ferraro, Nathanael Chambers, Niranjan Balasubramanian
| Challenge: | Existing models that understand narratives should infer these implicit states and their causal relationships with the narrative's explicit events. |
| Approach: | They propose a dataset that contains inferable participant states, a counterfactual perturbation to each state and the changes to the story that would be necessary if the counterfact was true. |
| Outcome: | The proposed model can reason about the impact of changes to the story that would be necessary if the counterfactual were true. |
DRP: Distilled Reasoning Pruning with Mathematical Skill-aware Step Decomposition for Efficient Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions to this problem are inference-time pruning and tuning-based distillation. |
| Approach: | They propose a framework that combines inference-time pruning with tuning-based distillation to enable efficient and accurate reasoning. |
| Outcome: | The proposed framework reduces token usage while improving accuracy on GSM8K and AIME tokens while avoiding performance drop. |
SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events (2024.findings-acl)
Copied to clipboard
| Challenge: | a recent study suggests that understanding goal-driven actions is challenging because of the small variations in the narrative that lead to vastly different goals, achievement outcomes and future actions. |
| Approach: | They propose to use a participant achievement lens to interpret and assess goal driven actions . they collect 6.3K high quality goal and action annotations reflecting their proposed lens . |
| Outcome: | The proposed lens can be used to interpret and assess goal driven actions . it can be fine-tuned on the dataset to achieve performance surpassing larger models . |
Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models' (LLMs) performance is greatly inflated by memorization, a study finds . authors propose a framework to analyze how LLMs reason under different degrees of memory access. |
| Approach: | They propose a framework that allows large language models to reason under different degrees of memory access. |
| Outcome: | Evaluating GPT-4o, LLaMA3.3-70B, and DeepSeek V3 on character-centric story understanding benchmarks, they find up to a 45.2% accuracy drop under the Restrictive Setting. |
ADAPTIVE IE: Investigating the Complementarity of Human-AI Collaboration to Adaptively Extract Information on-the-fly (2025.coling-main)
Copied to clipboard
Ishani Mondal, Michelle Yuan, Anandhavelu N, Aparna Garimella, Francis Ferraro, Andrew Blair-Stanek, Benjamin Van Durme, Jordan Boyd-Graber
| Challenge: | 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. |
| Approach: | They propose a framework that uses human-in-the-loop refinement to adapt to changing user questions. |
| Outcome: | The proposed framework is domain-agnostic, responsive, efficient for helping users access useful information while quickly reorganizing information in response to evolving information needs. |
Semantically-informed Hierarchical Event Modeling (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing approaches to event modeling combine sequential latent variables with semantic ontological knowledge to improve representational capabilities. |
| Approach: | They propose a doubly hierarchical semi-supervised event modeling framework that provides structural hierarchy while accounting for ontological hierarchy. |
| Outcome: | The proposed model outperforms state-of-the-art models by 8.5% across two datasets and four metrics. |
SAGEViz: SchemA GEneration and Visualization (2023.emnlp-demo)
Copied to clipboard
Sugam Devare, Mahnaz Koupaee, Gautham Gunapati, Sayontan Ghosh, Sai Vallurupalli, Yash Kumar Lal, Francis Ferraro, Nathanael Chambers, Greg Durrett, Raymond Mooney, Katrin Erk, Niranjan Balasubramanian
| Challenge: | Schema induction involves creating a graph representation depicting how events unfold . supervised and few-shot approaches are not scalable and time-consuming . |
| Approach: | They propose a tool that utilizes human-AI collaboration to create and update complex schema graphs efficiently. |
| Outcome: | The proposed tool can generate schemas of better quality and be used by users in a variety of domains. |
WikiVideo: Article Generation from Multiple Videos (2026.findings-acl)
Copied to clipboard
Alexander Martin, Reno Kriz, William Gantt Walden, Kate Sanders, Hannah Recknor, Eugene Yang, Francis Ferraro, Benjamin Van Durme
| Challenge: | Existing methods for retrieval-augmented generation focus on text rather than video. |
| Approach: | They propose a benchmark to generate Wikipedia-style articles from multiple videos . they propose 'collaborative article generation' that leverages an r1-style reasoning model and a VideoLLM to draw higher-level inferences about the target event than is possible with VideoLLms alone. |
| Outcome: | The proposed method outperforms existing methods in oracle retrieval and RAG settings while suggesting promising avenues for future work. |
Event Representation with Sequential, Semi-Supervised Discrete Variables (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for event modeling take discrete, external knowledge into account . obtaining fully accurate structured knowledge can be difficult . |
| Approach: | They propose a method that takes partially-observed sequences of discrete, external knowledge into account. |
| Outcome: | The proposed method outperforms baselines and state-of-the-art in script induction and converges faster. |
POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex Events (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing language models lag behind human performance in subtle ways in understanding complex situations, e.g., if the Argentine government yields to [IMF] pressure to rescind emergency legislation meant to protect ordinary families like the Brofmans. |
| Approach: | They propose to pre-identify a participant in a complex event and annotate their volitional engagement in causing the situation. |
| Outcome: | The proposed model can be used to infer the collective impact of salient events that make up a complex event, annotate volitional engagement of participants, and ground the outcome in state changes of the participants. |
The Universal Decompositional Semantics Dataset and Decomp Toolkit (2020.lrec-1)
Copied to clipboard
Aaron Steven White, Elias Stengel-Eskin, Siddharth Vashishtha, Venkata Subrahmanyan Govindarajan, Dee Ann Reisinger, Tim Vieira, Keisuke Sakaguchi, Sheng Zhang, Francis Ferraro, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme
| Challenge: | Decompositional semantics is a method of crowd-sourcing semantic annotations while retaining high interannotator agreement. |
| Approach: | They present the Universal Decompositional Semantics dataset (v1.0) they propose a decomposition-aligned approach to semantic annotation that uses simple questions to answer . |
| Outcome: | The dataset is bundled with the Decomp toolkit (v0.1) both datasets are publicly available at http://decomp.io. |