Papers by Armineh Nourbakhsh
“What is the value of templates?” Rethinking Document Information Extraction Datasets for LLMs (2024.findings-emnlp)
Copied to clipboard
Ran Zmigrod, Pranav Shetty, Mathieu Sibue, Zhiqiang Ma, Armineh Nourbakhsh, Xiaomo Liu, Manuela Veloso
| Challenge: | Existing work on prompt-response datasets for visually rich document understanding (VRDU) is labor-intensive. |
| Approach: | They propose a set of questions that are transformed from a key information extraction template to a prompt-response format using a plethora of bespoke templates. |
| Outcome: | The proposed datasets are compared with baseline models on K2Q with zero-shot prompting. |
DocLLM: A Layout-Aware Generative Language Model for Multimodal Document Understanding (2024.acl-long)
Copied to clipboard
Dongsheng Wang, Natraj Raman, Mathieu Sibue, Zhiqiang Ma, Petr Babkin, Simerjot Kaur, Yulong Pei, Armineh Nourbakhsh, Xiaomo Liu
| Challenge: | Documents with rich layouts are a significant portion of enterprise corpora and document AI is still a challenge. |
| Approach: | They propose a lightweight extension to traditional large language models for reasoning over visual documents that takes into account both textual semantics and spatial layout. |
| Outcome: | The proposed model outperforms existing large language models on 14 out of 16 datasets and generalizes well to 4 out of 5 previously unseen datasets. |
CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation (2025.acl-long)
Copied to clipboard
Santosh T.y.s.s, Youssef Tarek Elkhayat, Oana Ichim, Pranav Shetty, Dongsheng Wang, Zhiqiang Ma, Armineh Nourbakhsh, Xiaomo Liu
| Challenge: | LLMs can provide key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfaithful, ungrounded, or hallucinatory outputs. |
| Approach: | They propose a Confidence-guided copy-based decoding strategy that dynamically interpolates the model produced vocabulary distribution with a distribution derived based on copying from the context. |
| Outcome: | The proposed method outperforms existing context-aware decoding methods on five legal benchmarks. |
AliGATr: Graph-based layout generation for form understanding (2024.findings-emnlp)
Copied to clipboard
| Challenge: | State of the art forms understanding models often rely on poorly calibrated output probabilities and low performance on relation extraction tasks. |
| Approach: | They propose a graph-based model that uses a generative objective to represent complex grid-like layouts that are often found in forms. |
| Outcome: | The proposed model performs better on the KIE and RE tasks and is more accurate than existing models. |
Where is this coming from? Making groundedness count in the evaluation of Document VQA models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Document Visual Question Answering (VQA) models have come close to or matching human performance on some benchmarks. |
| Approach: | They propose a method that accounts for the semantic and multimodal groundedness of a model’s outputs and can be parameterized so that users can configure the score according to their preferences. |
| Outcome: | The proposed method produces scores that are a better indicator of a model’s robustness and tends to give higher rewards to better-calibrated answers. |
Improving compositional generalization for multi-step quantitative reasoning in question answering (2022.emnlp-main)
Copied to clipboard
| Challenge: | Quantitative reasoning is an important aspect of question answering when numeric and verbal cues interact to indicate sophisticated, multi-step programs. |
| Approach: | They propose a method that encourages QA models to adjust attention patterns and capture input/output alignments that are meaningful to the reasoning task. |
| Outcome: | The proposed approach improves program accuracy and renders models more robust against overfitting as the number of reasoning steps grows. |
Using counterfactual contrast to improve compositional generalization for multi-step quantitative reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | In quantitative question answering, compositional generalization is one of the main challenges of state of the art models. |
| Approach: | They propose a method that uses counterfactual scenarios to generate samples with compositional contrast. |
| Outcome: | The proposed method improves the performance of three state of the art models on four recently released datasets and also improves OOD performance on unseen domains and unsealed compositions. |
Towards a new research agenda for multimodal enterprise document understanding: What are we missing? (2024.findings-acl)
Copied to clipboard
| Challenge: | In this paper, we discuss the limitations of multimodal document understanding models in enterprise settings. |
| Approach: | They propose a research agenda that is aimed at driving the field towards higher impact in enterprise applications. |
| Outcome: | The proposed research agenda is aimed at driving the field towards higher impact in enterprise applications. |