Papers by Prafulla Kumar Choubey
In Plain Sight: Media Bias Through the Lens of Factual Reporting (D19-1)
Copied to clipboard
| Challenge: | lexical bias stems from content realization, or how things are said, but other forms of bias stem from content selection and organization. |
| Approach: | They use a dataset to analyze news articles annotated with 1,727 bias spans to investigate informational bias. |
| Outcome: | The proposed model shows that informational bias appears more frequently than lexical bias. |
Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that the hierarchical model learns to segment a document into subtopics and improves performance on the news discourse profiling task. |
| Approach: | They propose a hierarchical neural network that models multi-level interaction between sentences, subtopics, and the document. |
| Outcome: | The proposed model outperforms the existing model on the news discourse profiling task. |
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event (2020.acl-main)
Copied to clipboard
| Challenge: | a recent study shows that news articles report context-informing content that is not necessarily relevant to main events. |
| Approach: | They propose to use a functional discourse structure for news articles to model news content structures . they propose to integrate system predicted news structures into the annotations . |
| Outcome: | The proposed model outperforms existing models in event coreference resolution. |
Modeling Document-level Causal Structures for Event Causal Relation Identification (N19-1)
Copied to clipboard
| Challenge: | a study aims to identify all the event causal relations in a document, both within a sentence and across sentences . main challenges for achieving comprehensive causal relation identification are sparse among all possible event pairs . few causal relations are explicitly stated, especially for identifying cross-sentence causal relations . |
| Approach: | They propose to identify all event causal relations in a document, both within a sentence and across sentences. |
| Outcome: | The proposed model improves the performance of causal relation identification . it shows that the model can be used to identify cross-sentence causal relations . |
Automatic Data Acquisition for Event Coreference Resolution (2021.eacl-main)
Copied to clipboard
| Challenge: | lexical paraphrases and high precision rules informed by news discourse structure can be used to collect coreferential and non-coreferential event pairs from unlabeled English news articles. |
| Approach: | They propose to use lexical paraphrases and news discourse structure to automatically collect coreferential and non-coreferential event pairs from unlabeled English news articles. |
| Outcome: | The proposed model performs better than the supervised model on evaluation datasets with different event domains and text genres. |
Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination (2026.acl-industry)
Copied to clipboard
Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit, Jiaxin Zhang, Vaibhav Vats, Yu Li, Xiangyu Peng, Chien-Sheng Wu
| Challenge: | Enterprise deep research systems fail to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. |
| Approach: | They propose a scalable Enterprise Deep Research (EDR) architecture that decomposes requests into coverage-driven objectives via outline generation with reflection and localizes context with dependency-guided execution and explicit information sharing. |
| Outcome: | The proposed system achieves the strongest overall performance compared with competitive deep-research baselines on internal sales enablement tasks and the public DeepResearch Bench benchmark. |
One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing word-specific classifiers lack the ability to generalize across words and require limited sense-annotated data for every word. |
| Approach: | They propose to learn a single model that derives sense representations and enforces congruence between a word instance and its right sense by using both sense-annotated data and lexical resources. |
| Outcome: | Empirical evaluation shows the proposed model outperforms classifier-based models by 1.7%, 2.5% and 3.8% in F1-score on GloVe, ELMo and BERT word embeddings respectively. |
Improving Dialogue State Tracking by Discerning the Relevant Context (N19-1)
Copied to clipboard
| Challenge: | Dialog state tracking (DST) is used to estimate user's goals and requests in order to plan next action and respond accordingly. |
| Approach: | They propose a framework that uses the current user utterance and the most recent system utterant to determine the relevance of a system . Specifically, they use the current and most recent user . and system adverbs to determine relevance. |
| Outcome: | The proposed framework improves goal accuracy by 2.75% and 2.36% on WoZ 2.0 and Multi-WoZ restaurant domain datasets over the previous state-of-the-art GLAD model. |
Predicting Sentence Deletions for Text Simplification Using a Functional Discourse Structure (2022.acl-short)
Copied to clipboard
| Challenge: | Document-level text simplification often deletes some sentences to reduce text complexity. |
| Approach: | They use a news genre-specific functional discourse structure to predict sentence deletions . they incorporate sentence categories into a neural net model to improve recall . |
| Outcome: | The proposed model improves the recall of deletion prediction by 6.5% and 10.7%, and the overall F1 score by 3.6% and 4.3% respectively. |
Conformal Predictor for Improving Zero-Shot Text Classification Efficiency (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification. |
| Approach: | They propose to limit the number of likely labels using a fast base classifier-based conformal predictor calibrated on samples labeled by the 0shot model. |
| Outcome: | The proposed models reduce the average inference time for NLI- and NSP-based models by 25.6% and 22.2% without dropping performance below the predefined error rate of 1%. |
Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations (N18-2)
Copied to clipboard
| Challenge: | Identifying the most dominant and central event of a document is useful for many applications, says a new study . identifying the most prominent event in a news article is useful in text summarization, storyline generation and text segmentation. |
| Approach: | They propose to detect the most dominant and central event of a document . central event usually has many coreferential event mentions scattered throughout document a . |
| Outcome: | The proposed task can detect the most dominant and central event in a document . it can be used for text summarization, storyline generation and text segmentation . |
GTA: Generating Long-horizon Tasks for Web Agents at Scale (2026.acl-long)
Copied to clipboard
Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May, Chien-Sheng Wu
| Challenge: | Existing benchmarks provide only coarse start–goal annotations without intermediate trajectories . Existing frameworks provide no supervision over the agent's latent decision process . |
| Approach: | They propose a framework that integrates crawling, retrieval-based seeding, in-context generation and automated quality control to produce realistic tasks paired with executable trajectories. |
| Outcome: | The proposed framework decouples crawling from generation for greater efficiency and ensures dense supervision through deterministic replays and systematic validation. |
Benchmarking Deep Search over Heterogeneous Enterprise Data (2025.emnlp-industry)
Copied to clipboard
Prafulla Kumar Choubey, Xiangyu Peng, Shilpa Bhagavath, Kung-Hsiang Huang, Caiming Xiong, Chien-Sheng Wu
| Challenge: | Existing methods struggle to conduct deep searches and retrieve all necessary evidence. |
| Approach: | They propose a benchmark for evaluating deep search, a retrieval-augmented generation that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. |
| Outcome: | The proposed benchmarks show that even the best-performing agentic RAG methods achieve an average performance score of 32.96 on the benchmark. |
GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on gender bias in neural machine translation (NMT) incorrectly gendered translations can reflect or amplify social biases. |
| Approach: | They propose to use a monolingual corpus to generate gender-specific pseudo-parallel corpora and filter them to improve gender translation accuracy. |
| Outcome: | The proposed approach improves gender accuracy without damaging generic quality on translations from English into five languages. |
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents (2025.findings-acl)
Copied to clipboard
Prafulla Kumar Choubey, Xiangyu Peng, Shilpa Bhagavath, Caiming Xiong, Shiva Kumar Pentyala, Chien-Sheng Wu
| Challenge: | Existing workflow extraction methods for service agents are time-consuming and outdated, causing inconsistent and inconsistent results. |
| Approach: | They propose a framework for extracting and evaluating dialog workflows from historical interactions. |
| Outcome: | The proposed framework improves workflow extraction by 12.16% over baseline. |
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles (2024.naacl-long)
Copied to clipboard
Kung-Hsiang Huang, Philippe Laban, Alexander Fabbri, Prafulla Kumar Choubey, Shafiq Joty, Caiming Xiong, Chien-Sheng Wu
| Challenge: | Existing studies on multi-document summarization focus on collating information that all sources agree upon, but the task of summarizing diverse information remains underexplored. |
| Approach: | They propose a task of summarizing diverse information encountered in multiple news articles encompassing the same event using a dataset curated by a large language model. |
| Outcome: | The proposed task aims to summarize diverse information in multiple news articles encompassing the same event . the proposed task is difficult due to its limited coverage and verbosity biases . |
Unanswerability Evaluation for Retrieval Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation frameworks for retrieval-augmented generation (RAG) systems focus on answerable queries, but ignore the importance of appropriately rejecting unanswerable requests. |
| Approach: | They propose a framework to evaluate whether retrieval-augmented generation systems handle unanswerable queries specific to a given knowledge base. |
| Outcome: | The proposed framework synthesizes diverse and challenging queries for any given knowledge base and evaluates them with unanswered ratio and acceptable ratio metrics. |
Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures (P18-1)
Copied to clipboard
| Challenge: | a novel approach for event coreference resolution models correlations between event chains and document topical structures. |
| Approach: | They propose a novel approach that models correlations between event coreference chains and document topical structures through an Integer Linear Programming formulation. |
| Outcome: | The proposed approach improves performance across a dataset of document topics . it shows that the models can identify and link event mentions that refer to the same event . |
Improving Factual Consistency in Summarization with Compression-Based Post-Editing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve factual consistency of summarization models fail to remove entity errors if a suitable input entity replacement is not available or insert erroneous content. |
| Approach: | They propose to remove extrinsic entity errors, or entities not in the source, to improve consistency while retaining the summary’s essential information and form. |
| Outcome: | The proposed model improves factual consistency while maintaining ROUGE, improving entity precision by up to 30% on XSum, and can be applied on top of another post-editor, improving accuracy by 38%. |
Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs (2022.aacl-short)
Copied to clipboard
| Challenge: | Using news discourse profiling, we can identify temporal relationships between events and time expressions that are temporally related and otherwise difficult to locate. |
| Approach: | They propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs. |
| Outcome: | The proposed model can identify distant inter-sentence event and (or) time expression pairs that are temporally related and otherwise difficult to locate. |
CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work suggests that the degree of hallucination depends on factual errors in training data. |
| Approach: | They propose a method to use training data to reduce hallucination by ensembling parameter variations in training data. |
| Outcome: | The proposed method improves on XSUM and CNN/DM datasets on human evaluations and factual metrics. |
Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluations of retrieval-augmented generation systems are limited . sub-question coverage measures how well a RAG system addresses different facets of a question. |
| Approach: | They propose a framework for evaluation based on sub-question coverage . they propose to decompose questions into sub-questions and classify them into three types . |
| Outcome: | The proposed evaluation framework measures how well a RAG system addresses different facets of a question. |