Papers by Franck Dernoncourt
LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles (2025.findings-emnlp)
Copied to clipboard
Ho Yin Sam Ng, Edward Hsu, Aashish Anantha Ramakrishnan, Branislav Kveton, Nedim Lipka, Franck Dernoncourt, Dongwon Lee, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ting-Hao Kenneth Huang
| Challenge: | Figure captions are crucial for helping readers understand and remember a figure’s key message. |
| Approach: | They propose a dataset for personalized figure caption generation with multimodal figure profiles that provide inputs and profiles for each figure . |
| Outcome: | The proposed dataset provides inputs and profiles for personalized figure caption generation with multimodal figure profiles. |
Rethinking Self-Attention: Towards Interpretability in Neural Parsing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work shows that attention mechanisms provide arguably explainable attention distributions that can help to interpret predictions. |
| Approach: | They propose a new self-attention layer where attention heads represent labels. |
| Outcome: | The proposed model obtains state-of-the-art results on the Penn Treebank and Chinese Treebank. |
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes. |
| Approach: | They assemble and publish a multilingual Twitter corpus for the task of hate speech detection using inferred author demographic factors. |
| Outcome: | The results show that the classifiers learn human biases and can be discriminatory towards certain demographic groups. |
ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Existing frameworks for large language model embeddings have limited support for only a limited range of architectures and fine-tuning strategies. |
| Approach: | They propose a framework that enables bidirectional attention across various LLMs and supports a range of fine-tuning strategies. |
| Outcome: | The proposed framework enables bidirectional attention across various LLMs and supports a range of fine-tuning strategies. |
Hybrid Knowledge Transfer for Improved Cross-Lingual Event Detection via Hierarchical Sample Selection (2023.acl-long)
Copied to clipboard
| Challenge: | Recent efforts to train cross-lingual models on source language fail to take advantage of data transfer . current methods focus on learning task-specific information from syntactical features or word-label relations in target language. |
| Approach: | They propose a hybrid knowledge-transfer approach that leverages a teacher-student framework . the model is evaluated on a distinct target language for which there is no labeled data . |
| Outcome: | The proposed model achieves state-of-the-art results on 9 morphologically-diverse target languages across 3 distinct datasets. |
Hierarchical Selection of Important Context for Generative Event Causality Identification with Optimal Transports (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for Event Causality Identification (ECI) rely on external toolkits or human annotation to obtain training signals. |
| Approach: | They propose a generative framework that leverages Optimal Transport to automatically select the most important sentences and words from full documents. |
| Outcome: | The proposed framework can predict causal relation between two events in text without external tools. |
Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents (2025.emnlp-main)
Copied to clipboard
Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi, Vivek Gupta, Dinesh Manocha
| Challenge: | Flowcharts are a critical tool for visualizing decision-making processes, but their non-linear structure and complex visual-textual relationships make it difficult to interpret them using LLMs. |
| Approach: | They propose a task of Fine-grained Flowchart Attribution to trace components grounding a flowchart referring LLM response. |
| Outcome: | The proposed agent mitigates visual hallucinations in LLM answers over baselines by 10–14% on a FlowExplainBench dataset. |
Curricular Next Conversation Prediction Pretraining for Transcript Segmentation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Prior research on document segmentation has focused on segmenting documents such as Wikipedia articles. |
| Approach: | They propose to pretrain a model to identify consecutive conversations to address these challenges . they introduce a curriculum to Advanced NCP to make the task more relevant to the downstream task . |
| Outcome: | The proposed model outperforms previous models in speech recognition errors and is robust to speech recognition. |
Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes (2025.naacl-short)
Copied to clipboard
Isabel O. Gallegos, Ryan Aponte, Ryan A. Rossi, Joe Barrow, Mehrab Tanjim, Tong Yu, Hanieh Deilamsalehy, Ruiyi Zhang, Sungchul Kim, Franck Dernoncourt, Nedim Lipka, Deonna Owens, Jiuxiang Gu
| Challenge: | Large language models exhibit harmful social biases, but they are often difficult to train and modify. |
| Approach: | They leverage the zero-shot capabilities of large language models to reduce stereotyping . they introduce a technique called zero- shot self-debiasing to reduce bias . |
| Outcome: | The proposed technique reduces stereotyping across nine different social groups while relying on the LLM itself and a simple prompt. |
Multimodal Intent Discovery from Livestream Videos (2022.findings-naacl)
Copied to clipboard
Adyasha Maharana, Quan Tran, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Mohit Bansal
| Challenge: | Existing models for instructional video understanding struggle to understand abstract intents . identifying procedural intent within instructional videos is a challenging task . |
| Approach: | They propose to extract instructional intent from software instructional livestreams by using a multimodal cascaded cross-attention model that integrates weaker and noisier video signals with more discriminative text signals. |
| Outcome: | The proposed model improves on baseline models and compares it to existing models. |
Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing question-answering models do not require reasoning across sentences in the given context (passage). |
| Approach: | They propose a graph neural network that propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation. |
| Outcome: | The proposed approach obtains the best performance compared to the widely used answer-selection models that do not consider the intersentential relationship. |
Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for subevent relation extraction (SRE) focus on sequential order of words in texts to enhance representation learning. |
| Approach: | They propose a method that learns to induce effective graph structures for input texts . they use word alignment frameworks with dependency paths and optimal transport . |
| Outcome: | The proposed method is able to induce effective graph structures for input texts to boost representation learning. |
Test-Time Strategies for More Efficient and Accurate Agentic RAG (2026.acl-srw)
Copied to clipboard
Abhinav Sharma, Brian Zhang, Deepti Guntur, Zhiyang Zuo, Shreyas Chaudhari, Wenlong Zhao, Franck Dernoncourt, Puneet Mathur, Ryan A. Rossi, Nedim Lipka
| Challenge: | Retrieval-Augmented Generation (RAG) systems face challenges with complex, multi-hop questions. |
| Approach: | They propose to integrate contextualization module and de-duplication module to improve the accuracy of retrieved documents and to reduce the number of turns by 10.5%. |
| Outcome: | The proposed approach achieves a 5.6% increase in EM score and reduces the average number of turns by 10.5% compared to the baseline. |
PSED: A Dataset for Selecting Emphasis in Presentation Slides (2021.findings-acl)
Copied to clipboard
Amirreza Shirani, Giai Tran, Hieu Trinh, Franck Dernoncourt, Nedim Lipka, Jose Echevarria, Thamar Solorio, Paul Asente
| Challenge: | null |
| Approach: | null |
| Outcome: | null |
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases (2025.findings-acl)
Copied to clipboard
Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, Yu Wang
| Challenge: | Existing methods for textual and structural retrieval ignore mutual reinforcement and only use structural retrievals for text-rich Graph Knowledge Bases (TG-KBs). |
| Approach: | They propose a Mixture of Structural-and-Textual Retrieval to retrieve textual and structural knowledge via a Planning-Reasoning-Organizing framework. |
| Outcome: | Experiments show that the proposed framework performs better than existing methods in analyzing TG-KBs and integrating structural trajectories for candidate reranking. |
MeetingQA: Extractive Question-Answering on Meeting Transcripts (2023.acl-long)
Copied to clipboard
| Challenge: | Meeting transcripts are a promising domain for natural language tasks . lack of annotated data impedes research on other important tasks in this domain . |
| Approach: | They propose an extractive QA dataset comprising questions asked by meeting participants and corresponding responses. |
| Outcome: | The proposed dataset extracts questions asked by meeting participants and corresponding responses from transcripts. |
A Survey on LLM-based Conversational User Simulation (2026.eacl-long)
Copied to clipboard
Bo Ni, Yu Wang, Leyao Wang, Branislav Kveton, Franck Dernoncourt, Yu Xia, Hongjie Chen, Reuben Luera, Samyadeep Basu, Subhojyoti Mukherjee, Puneet Mathur, Nesreen K. Ahmed, Junda Wu, Li Li, Huixin Zhang, Ruiyi Zhang, Tong Yu, Sungchul Kim, Jiuxiang Gu, Zhengzhong Tu, Alexa Siu, Zichao Wang, Seunghyun Yoon, Nedim Lipka, Namyong Park, Zihao Lin, Trung Bui, Yue Zhao, Tyler Derr, Ryan A. Rossi
| Challenge: | Recent advances in large language models (LLMs) have enabled high-fidelity generation of synthetic user conversation. |
| Approach: | They propose a taxonomy covering user granularity and simulation objectives . they analyze core techniques and evaluation methodologies to help them understand the latest developments . |
| Outcome: | The proposed model enables high-fidelity generation of synthetic user conversation. |
Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision (2022.coling-1)
Copied to clipboard
Khalil Mrini, Harpreet Singh, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter W. Chang, Emilia Farcas, Ndapa Nakashole
| Challenge: | Current medical question answering systems have difficulty processing long, detailed and informally worded questions . a growing number of approaches attempt to enhance the processing of consumer health questions - or medical question understanding . |
| Approach: | They propose a medical question understanding and answering system with knowledge grounding and semantic self-supervision that matches a user question with a trusted medical knowledge base and retrieves a fixed number of relevant sentences from the corresponding answer document. |
| Outcome: | The proposed system retrieves more relevant answers while achieving 20 times faster. |
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning (2021.acl-short)
Copied to clipboard
| Challenge: | BERTScore and other text generation metrics do not use reference captions to evaluate image captions. |
| Approach: | They propose a new metric which does not require reference captions to evaluate image captions . they train UMIC to discriminate negative captions via contrastive learning . |
| Outcome: | The proposed metric has higher correlation than previous metrics that require multiple references. |
Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Subquadratic architectures rely on aggressive state compression that degrades performance on complex reasoning tasks. |
| Approach: | They propose a framework that confers fixed-memory inference onto pretrained Transformers . they use a learnable module that enforces an adaptive sparsity policy over the context history . |
| Outcome: | The proposed framework outperforms state-of-the-art linearized baselines on the GSM8K benchmark by over 36 points under identical memory constraints. |
BehancePR: A Punctuation Restoration Dataset for Livestreaming Video Transcript (2022.findings-naacl)
Copied to clipboard
| Challenge: | a growing number of livestreaming videos provide useful knowledge with exceptional visual demonstrations. |
| Approach: | They propose a human-annotated corpus for punctuation restoration in livestreaming video transcripts . they show popular natural language processing tools underperform on sentence boundary detection . |
| Outcome: | The proposed dataset shows that natural language processing tools underperform on sentence boundary detection on livestreaming video transcripts. |
Let Me Choose: From Verbal Context to Font Selection (2020.acl-main)
Copied to clipboard
| Challenge: | Current font selection interfaces do not consider verbal context of the input text. |
| Approach: | They propose a dataset containing examples of different topics in social media posts and ads, labeled through crowd-sourcing. |
| Outcome: | The proposed model captures inter-subjectivity across annotations on a dataset of social media posts and ads labeled through crowd-sourcing. |
Event Extraction in Video Transcripts (2022.coling-1)
Copied to clipboard
| Challenge: | Existing EE datasets are limited to formally written documents such as news articles or scientific papers . existing EE methods and datasets cannot be used in informal and noisy texts . |
| Approach: | They propose to use video transcripts as a dataset for event extraction . they demonstrate that existing state-of-the-art EE methods cannot achieve adequate performance . |
| Outcome: | The proposed dataset evaluates state-of-the-art EE methods on streamed videos on Behance . it shows that such systems cannot achieve adequate performance on the proposed dataset . |
Virtual Knowledge Graph Construction for Zero-Shot Domain-Specific Document Retrieval (2022.coling-1)
Copied to clipboard
| Challenge: | Domain-specific documents cover terminologies and specialized knowledge. |
| Approach: | They propose a domain-specific document retrieval method that embeds a document into a graph of entities and their relations into . they compare the unsupervised method with previous approaches and use it to compute relevance between queries and documents. |
| Outcome: | The proposed method outperforms baselines and fully-supervised bi-encoders in a zero-shot setting and outperformed bi-supervised approaches. |
TIMERS: Document-level Temporal Relation Extraction (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for temporal relation extraction focus on extracting temporal relations between event pairs present in the same sentence or adjacent sentences, mostly ignoring document-level pairs. |
| Approach: | They propose a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language that leverages rhetorical discourse features and temporal arguments from semantic role labels. |
| Outcome: | The proposed model outperforms previous methods on the TDDiscourse, TimeBank-Dense, and MATRES datasets due to its discourse-level modeling. |
MACRONYM: A Large-Scale Dataset for Multilingual and Multi-Domain Acronym Extraction (2022.coling-1)
Copied to clipboard
Amir Pouran Ben Veyseh, Nicole Meister, Seunghyun Yoon, Rajiv Jain, Franck Dernoncourt, Thien Huu Nguyen
| Challenge: | Acronym extraction is the task of identifying acronyms and their expanded forms in texts . existing AE methods for English are limited to specific languages and domains . |
| Approach: | They propose to annotate 27,200 sentences in 6 different languages and 2 new domains for AE. |
| Outcome: | The proposed dataset shows that AE in different languages and learning settings has unique challenges . |
KPQA: A Metric for Generative Question Answering Using Keyphrase Weights (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing n-gram similarity metrics fail to discriminate the incorrect answers due to the free-form of the answer. |
| Approach: | They propose a new metric that assigns different weights to each token via keyphrase prediction to judge the correctness of GenQA. |
| Outcome: | The proposed metric has a significantly higher correlation with human judgments than existing metrics in various datasets. |
Analyzing Sentence Fusion in Abstractive Summarization (D19-54)
Copied to clipboard
Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim, Seokhwan Kim, Walter Chang, Fei Liu
| Challenge: | Abstractive summarization systems struggle to combine information from multiple sources, resulting in poor grammar and incorrect facts. |
| Approach: | They analyze the outputs of five abstractive summarization systems and examine their grammatical accuracy and faithfulness. |
| Outcome: | The proposed summarization systems are able to combine information from multiple sources, but they often fail to remain faithful to the original document. |
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models (2021.naacl-main)
Copied to clipboard
Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu
| Challenge: | Recent studies indicate that NLU models are prone to rely on shortcut features for prediction, without achieving true language understanding. |
| Approach: | They propose a shortcut mitigation framework to suppress NLU models from making overconfident predictions for samples with large shortcut degree. |
| Outcome: | The proposed framework suppresses the model from making overconfident predictions for samples with large shortcut degree. |
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)
Copied to clipboard
Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley
| Challenge: | Large Language Models (LLMs) have been used for selection and training of data for active learning. |
| Approach: | They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop. |
| Outcome: | The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances. |
A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing systems that perform content selection and surface realization are not able to provide sufficient training data for news summarization. |
| Approach: | They propose to use a cascade architecture to perform content selection and surface realization together to generate abstracts. |
| Outcome: | The proposed architecture outperforms or outranks existing systems in terms of content selection and surface realization. |
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams (2026.acl-long)
Copied to clipboard
Jiyeon Kim, Hyunji Lee, Dylan Zhou, Sue Hyun Park, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Sungmin Cha, Minjoon Seo
| Challenge: | Existing models and agentic memory systems fail to adapt robustly to OAKS, demonstrating delays in state-tracking and susceptibility to distraction within streaming environments. |
| Approach: | They propose a benchmark to evaluate models' ability to adapt to changing knowledge over streaming . they use two datasets to analyze how facts evolve over time . |
| Outcome: | The proposed benchmark evaluates models in an online adaptation setting over streaming, continually updating knowledge. |
Document-Level Event Argument Extraction via Optimal Transport (2022.findings-acl)
Copied to clipboard
| Challenge: | Prior work on event-level EAE models ignore syntactic structures for documents . prior work on EE is restricted to sentence-level setting where event triggers and arguments are assumed to appear in the same sentences. |
| Approach: | They propose to employ Optimal Transport to induce structures of documents based on sentence-level syntactic structures and tailored to EAE task. |
| Outcome: | The proposed model is effective in document-level EAE, with a new constraint on unrelated context words. |
DocScript: Document-level Script Event Prediction (2024.lrec-main)
Copied to clipboard
Puneet Mathur, Vlad I. Morariu, Aparna Garimella, Franck Dernoncourt, Jiuxiang Gu, Ramit Sawhney, Preslav Nakov, Dinesh Manocha, Rajiv Jain
| Challenge: | Existing script event prediction frameworks such as ChatGPT and FlanT5 lack the ability to learn long-range dependencies between events. |
| Approach: | They propose a novel script event prediction task which aims to predict the next event from a candidate list of narrative events in long-form documents. |
| Outcome: | The proposed architecture can learn sequential ordering between events at the document scale. |
Keyphrase Prediction from Video Transcripts: New Dataset and Directions (2022.coling-1)
Copied to clipboard
Amir Pouran Ben Veyseh, Quan Hung Tran, Seunghyun Yoon, Varun Manjunatha, Hanieh Deilamsalehy, Rajiv Jain, Trung Bui, Walter W. Chang, Franck Dernoncourt, Thien Huu Nguyen
| Challenge: | Existing studies on keyphrase prediction have focused on formal texts and informal-text domains. |
| Approach: | They propose to annotate large-scale video transcripts with keyphrases from live-stream video . they propose to feed models with paragraph-level keyphrase extraction to foster future research . |
| Outcome: | The proposed model improves keyphrase prediction in live-stream video transcripts by feeding models with paragraph-level keyphrases. |
PDFTriage: Question Answering over Long, Structured Documents (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to document QA use a pre-retrieval step to retrieve the relevant context from documents, but this is incongruous with the user's mental model of the document. |
| Approach: | They propose an approach called PDFTriage that enables models to retrieve the context based on either structure or content. |
| Outcome: | The proposed approach can retrieve context based on structure or content across several classes of questions where existing retrieval-augmented LLMs fail. |
Unleash GPT-2 Power for Event Detection (2021.acl-long)
Copied to clipboard
| Challenge: | Event Detection (ED) aims to recognize mentions of events and their types in text. |
| Approach: | They propose to exploit a pre-trained language model to generate training samples for ED. |
| Outcome: | The proposed model improves on multiple ED benchmark datasets and establishes state-of-the-art results. |
Open-Domain Question Answering with Pre-Constructed Question Spaces (2021.naacl-srw)
Copied to clipboard
| Challenge: | Open-domain question answering aims at locating answers to user-generated questions in massive collections of documents. |
| Approach: | They propose an algorithm with a novel reader-retriever design that differs from both families of algorithms. |
| Outcome: | The proposed algorithm outperforms retrieval-based methods with two large-scale datasets and is state-of-the-art. |
Structured Uncertainty guided Clarification for LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to clarifying tasks fail when user instructions are ambiguous or incomplete. |
| Approach: | They propose a principled formulation of structured uncertainty that operates directly over tool parameters and their domains. |
| Outcome: | The proposed framework improves when2call accuracy and training-time sample efficiency. |
Lizard: An Efficient Linearization Framework for Large Language Models (2026.acl-long)
Copied to clipboard
Chien Van Nguyen, Huy Huu Nguyen, Ruiyi Zhang, Hanieh Deilamsalehy, Puneet Mathur, Viet Dac Lai, Haoliang Wang, Jayakumar Subramanian, Ryan A. Rossi, Trung Bui, Nikos Vlassis, Franck Dernoncourt, Thien Huu Nguyen
| Challenge: | Existing linearization frameworks that rely on softmax attention with quadratic time and memory complexity pose significant computational and memory bottlenecks for long-context applications. |
| Approach: | They propose a linearization framework that transforms pretrained Transformer-based Large Language Models into subquadratic architectures that closely approximate softmax attention while preserving model quality. |
| Outcome: | Experiments show that the proposed framework outperforms existing methods by 9.4 - 24.5 points on the 5-shot MMLU benchmark and demonstrating superior associative recall. |
Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation (N19-1)
Copied to clipboard
| Challenge: | a study of long documents that do not include short sections in their titles shows that they improve comprehension and speed . |
| Approach: | They propose to extract the most salient sentence and apply deletion-based compression to generate section titles in low-resource environments. |
| Outcome: | The proposed approach outperforms other methods in low-resource environments while outperforming other approaches. |
TutorialVQA: Question Answering Dataset for Tutorial Videos (2020.lrec-1)
Copied to clipboard
| Challenge: | a new question answering task on instructional videos is needed due to their verbose nature . factoid questions are only a small part of what people actually want to ask on video contents . |
| Approach: | They propose a question answering task on instructional videos based on video transcripts . they use a dataset consisting of 6,000 manually collected triples of (video, question, answer span) |
| Outcome: | The proposed task focuses on screencast tutorial videos pertaining to an image editing program. |
What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation (2020.coling-main)
Copied to clipboard
| Challenge: | Acronyms are short forms of phrases that facilitate conveying lengthy sentences in documents. |
| Approach: | They propose to annotate a large dataset for scientific domain and a new deep learning model which expands an ambiguous acronym in a sentence. |
| Outcome: | The proposed model outperforms the state-of-the-art models on the new dataset. |
Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for extractive summarization lack coherence, despite improvements . a human-annotated dataset is used to improve coherency of extractive summary . |
| Approach: | They propose to use human-annotated datasets to create coherent extractive summaries . they use supervised fine-tuning and natural language user feedback to enhance coherence . |
| Outcome: | The proposed dataset shows that LLMs can produce coherent summaries with human feedback. |
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions (P19-1)
Copied to clipboard
Amirreza Shirani, Franck Dernoncourt, Paul Asente, Nedim Lipka, Seokhwan Kim, Jose Echevarria, Thamar Solorio
| Challenge: | Visual communication relies heavily on images and short texts to grab a viewer's attention and convey a message in the most efficient way. |
| Approach: | They propose a model that employs end-to-end label distribution learning on crowd-sourced data and predicts a selection distribution, capturing the inter-subjectivity and ambiguity of the input. |
| Outcome: | The proposed model captures the inter-subjectivity and ambiguity of the input and can be transformed to single-label learning by mapping labels to absolute labels via majority voting. |
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (N18-2)
Copied to clipboard
Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, Nazli Goharian
| Challenge: | Existing abstractive summarization models focus on summarizing sentences and short documents. |
| Approach: | They propose a hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary. |
| Outcome: | The proposed model significantly outperforms state-of-the-art models on two large-scale datasets of scientific papers. |
Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing models for toxic span detection only classify text snippets as offensive or not . a novel model seeks to simultaneously predict offensive words and opinion phrases . |
| Approach: | They propose a novel model that seeks to predict offensive words and opinion phrases simultaneously . they also introduce a regularization mechanism to encourage consistency of the model predictions . |
| Outcome: | The proposed model performs well compared to baselines on toxic span detection tasks . it predicts offensive words and opinion phrases to leverage inter-dependencies . |
SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment (2023.findings-acl)
Copied to clipboard
Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin
| Challenge: | Existing methods for multimodal summarization ignore the structure and semantics of the whole video and article. |
| Approach: | They propose a semantic-consistent cross-domain summarization model that extracts features from video and article and uses fusion methods to select representative one. |
| Outcome: | The proposed model produces high-quality multimodal summaries on three MSMO datasets. |
Syntopical Graphs for Computational Argumentation Tasks (2021.acl-long)
Copied to clipboard
Joe Barrow, Rajiv Jain, Nedim Lipka, Franck Dernoncourt, Vlad Morariu, Varun Manjunatha, Douglas Oard, Philip Resnik, Henning Wachsmuth
| Challenge: | adler and van Doren (1940) proposed a formalized manual process for understanding a topic based on multiple viewpoints. |
| Approach: | They propose a syntopical reading process that emphasizes comparing and contrasting viewpoints to improve topic understanding. |
| Outcome: | The proposed method outperforms approaches that do not use collection-level information. |
MadDog: A Web-based System for Acronym Identification and Disambiguation (2021.eacl-demos)
Copied to clipboard
| Challenge: | Acronyms and abbreviations are the short-form of longer phrases and are frequently used in writing but they can also present challenges for newcomers. |
| Approach: | They propose to develop a web-based acronym identification and disambiguation system which can process acronyms from various domains including scientific, biomedical, and general domains. |
| Outcome: | The proposed system can process acronyms from scientific, biomedical, and general domains. |
MECI: A Multilingual Dataset for Event Causality Identification (2022.coling-1)
Copied to clipboard
| Challenge: | Event Causality Identification (ECI) is a task of detecting causal relations between events mentioned in text. |
| Approach: | They propose a multilingual dataset that provides consistent annotations for event causality relations in five languages. |
| Outcome: | The proposed dataset provides consistent annotation guidelines for five languages . the dataset can provide ample research challenges and directions for future research . |
DocTime: A Document-level Temporal Dependency Graph Parser (2022.naacl-main)
Copied to clipboard
Puneet Mathur, Vlad Morariu, Verena Kaynig-Fittkau, Jiuxiang Gu, Franck Dernoncourt, Quan Tran, Ani Nenkova, Dinesh Manocha, Rajiv Jain
| Challenge: | Document dependency graphs (TDGs) are used to understand the temporal relations between events mentioned in a document and to improve downstream tasks such as timeline creation and time-aware summarization. |
| Approach: | They propose a temporal dependency graph parser that takes input from a text document and produces a graph that incorporates longer range dependencies. |
| Outcome: | The proposed framework outperforms existing models on three datasets and improves tasks such as timeline creation, time-aware summarization, and temporal information extraction. |
MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for ED in IE and NLP focus on feature-based models to feature-driven models. |
| Approach: | They propose to use a multilingual dataset to annotate events for 8 different languages . they demonstrate the challenges and transferability of ED across languages in MINION . |
| Outcome: | a new dataset that consistently annotates events for 8 different languages is released . the new dataset will promote future research on multilingual ED . |
A Repository of Corpora for Summarization (L18-1)
Copied to clipboard
| Challenge: | Summarization corpora are numerous but fragmented, making it difficult to pinpoint corporata best suited for a given summarization task. |
| Approach: | They propose a repository containing corpora available to train and evaluate automatic summarization systems. |
| Outcome: | The proposed system is based on a repository of corpora available for summarization tasks. |
Expressing Visual Relationships via Language (P19-1)
Copied to clipboard
| Challenge: | Current studies on image captioning focus on single image, but there are no effective models for generating relational captions for two images. |
| Approach: | They propose a language-guided image editing dataset that contains real image pairs with corresponding editing instructions. |
| Outcome: | The proposed model outperforms baseline and existing methods on two datasets. |
CORG: Generating Answers from Complex, Interrelated Contexts (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to analyzing knowledge in a corpus often focus on single factors in isolation. |
| Approach: | They propose a framework that organizes multiple contexts into independently processed groups . they classify these relationships into distracting, ambiguous, counterfactual, and duplicated . |
| Outcome: | The proposed framework outperforms existing grouping methods and single-context approaches. |
A Corpus for Detecting High-Context Medical Conditions in Intensive Care Patient Notes Focusing on Frequently Readmitted Patients (2020.lrec-1)
Copied to clipboard
Edward T. Moseley, Joy T. Wu, Jonathan Welt, John Foote, Patrick D. Tyler, David W. Grant, Eric T. Carlson, Sebastian Gehrmann, Franck Dernoncourt, Leo Anthony Celi
| Challenge: | Currently, most medical data is generated and stored in unstructured, text-based format. |
| Approach: | They propose to use a patient phenotyping dataset to identify whether a given medical condition is present in their notes. |
| Outcome: | The proposed dataset contains 1102 Discharge Summaries and 1000 Nursing Progress Notes. |
StreamHover: Livestream Transcript Summarization and Annotation (2021.emnlp-main)
Copied to clipboard
Sangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Walter Chang, Hailin Jin, Jonathan Brandt, Hassan Foroosh, Fei Liu
| Challenge: | StreamHover is a framework for annotating and summarizing livestream transcripts . the problem is that there is n't enough annotated datasets to summarize livestreams based on the informal nature of spoken language . |
| Approach: | They propose a framework for annotating and summarizing livestream transcripts using a text preview. |
| Outcome: | The proposed model generalizes better and improves over strong baselines. |
DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding (2024.emnlp-main)
Copied to clipboard
Manan Suri, Puneet Mathur, Franck Dernoncourt, Rajiv Jain, Vlad Morariu, Ramit Sawhney, Preslav Nakov, Dinesh Manocha
| Challenge: | Document structure editing involves manipulating localized textual, visual, and layout components in document images based on user’s requests. |
| Approach: | They propose a framework that performs end-to-end document editing by leveraging Large Multimodal Models (LMMs) by localizing edit regions of interest and disambiguating user edit requests into edit commands. |
| Outcome: | The proposed framework outperforms baselines on edit command generation (2-33%), RoI bounding box detection (12-31%), and overall document editing (1-12%) tasks. |
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback (2023.emnlp-demo)
Copied to clipboard
| Challenge: | Existing instruction-tuned open-source LLMs have only been instruction- tuned for English and a few popular languages, thus hindering their accessibility to many other languages in the world. |
| Approach: | They propose a framework that uses supervised fine-tuning and reinforcement learning from human feedback to improve the accessibility of large language models. |
| Outcome: | The proposed framework enables the evaluation of generative LLMs in multiple languages. |
OATS: A Challenge Dataset for Opinion Aspect Target Sentiment Joint Detection for Aspect-Based Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) focuses on understanding sentiments specific to distinct elements within a user-generated review. |
| Approach: | They propose to use Aspect-based sentiment analysis to understand specific aspects of a user-generated review to identify the target entity being reviewed, the aspect to which it belongs, the opinion phrase, and the sentiment expressed toward the aspects. |
| Outcome: | The proposed dataset bridges the gaps observed in existing datasets and sheds light on various ABSA subtasks. |
Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models that perform information extraction tasks manually assume heuristic dependency between the task instances and mean-field factorization for the joint distribution of instance labels. |
| Approach: | They propose to induce a dependency graph among task instances to boost representation learning by estimating their joint distribution via Conditional Random Fields. |
| Outcome: | The proposed model outperforms previous models on multiple IE tasks across 5 datasets and 2 languages. |
Learning Prototype Representations Across Few-Shot Tasks for Event Detection (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing training data for event detection are too expensive to achieve in real applications where novel event types emerge . Typical ED systems require labeled data for each predefined event type, but only a few examples are available. |
| Approach: | They propose to introduce cross-task prototypes to model relationships between training tasks in few-shot learning for event detection. |
| Outcome: | The proposed model improves on three few-shot learning datasets. |
Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on IE tasks that use two types of dependencies is not optimal . emr, event trigger detection, event argument extraction, and relation extraction are challenging . |
| Approach: | They propose a model that learns cross-task dependencies from data . they treat each task instance as a node in a dependency graph . |
| Outcome: | The proposed model outperforms strong baselines over four datasets with different languages. |
Using Visual Feature Space as a Pivot Across Languages (2020.findings-emnlp)
Copied to clipboard
| Challenge: | We show that models trained to generate textual captions in more than one language can leverage their jointly trained feature space during inference to pivot across languages. |
| Approach: | They show that models trained to generate captions in more than one language can leverage their jointly trained feature space during inference to pivot across languages. |
| Outcome: | The proposed approach improves quality of captions in German and English by leveraging captions from a second language. |
Understanding Points of Correspondence between Sentences for Abstractive Summarization (2020.acl-srw)
Copied to clipboard
| Challenge: | Using points of correspondence, fusion systems are difficult for abstractive summarizers because of their complexity. |
| Approach: | They propose to model points of correspondence between disparate sentences by combining documents, source and fusion sentences, and human annotations of points of correspondance between sentences. |
| Outcome: | The proposed model bridges the gap between coreference resolution and summarization by using human annotations of points of correspondence between sentences. |
MEE: A Novel Multilingual Event Extraction Dataset (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Event Extraction are limited for non-English languages . lack of high-quality multilingual datasets has been the main hindrance . |
| Approach: | They propose a multilingual event extraction dataset that provides annotation for more than 50K event mentions in 8 typologically different languages. |
| Outcome: | The proposed dataset provides annotation for more than 50K event mentions in 8 languages . the proposed dataset will be publicly available to foster future research . |
Scoring Sentence Singletons and Pairs for Abstractive Summarization (P19-1)
Copied to clipboard
Logan Lebanoff, Kaiqiang Song, Franck Dernoncourt, Doo Soon Kim, Seokhwan Kim, Walter Chang, Fei Liu
| Challenge: | Existing methods for summarizing content from single sentences are inadequately understood. |
| Approach: | They propose to combine singletons and pairs to create a summarizing sentence . they use a dataset of human-written abstracts to examine human-writing methods . |
| Outcome: | The proposed framework is based on human-written abstracts from three large datasets. |
BehanceCC: A ChitChat Detection Dataset For Livestreaming Video Transcripts (2022.lrec-1)
Copied to clipboard
| Challenge: | livestreaming videos contain a considerable amount of off-topic content, causing noises and data load to downstream applications. |
| Approach: | They propose a human-annotated benchmark dataset for off-topic detection in livestreaming video transcripts. |
| Outcome: | The proposed dataset reveals the complexity of chitchat detection in livestreaming videos . livestreams tend to be longer than pre-recorded videos and have fewer verbal pauses . |
MCECR: A Novel Dataset for Multilingual Cross-Document Event Coreference Resolution (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing datasets for event coreference resolution focus on within-document event coreference and English text, lacking cross-document ECR datasets beyond English. |
| Approach: | They propose a multiligual dataset that manually annotates documents for event mentions and coreference in five languages. |
| Outcome: | The proposed dataset annotates documents for event mentions and coreference in five languages . the dataset fetches related news articles from the google search engine to increase the number of non-singleton clusters . |
Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs (2026.findings-eacl)
Copied to clipboard
Paiheng Xu, Gang Wu, Xiang Chen, Tong Yu, Chang Xiao, Franck Dernoncourt, Tianyi Zhou, Wei Ai, Viswanathan Swaminathan
| Challenge: | Large Language Models (LLMs) can generate code from natural language queries, but runtime code generation is limited due to unverified code, security risks, longer response times, and higher computational costs. |
| Approach: | They propose an offline simulation framework to curate a software-specific skillset by exploiting large language models and publicly available scripting guides. |
| Outcome: | The proposed framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation. |
An Analysis of Multilingual FActScore (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in LLMs have demonstrated significant capabilities in many applications. |
| Approach: | They propose a dataset for FActScore on texts generated by strong multilingual LLMs and evaluate their performance in other languages. |
| Outcome: | The proposed dataset shows that LLMs exhibit distinct behaviors in fact extraction and fact scoring tasks. |
Transfer Learning for Named-Entity Recognition with Neural Networks (L18-1)
Copied to clipboard
| Challenge: | Existing approaches to named-entity recognition (NER) require additional lead time for developing and fine-tuning the rules. |
| Approach: | They propose to transfer an ANN model trained on a large labeled dataset to another dataset with a limited number of labels to improve upon the state-of-the-art results for patient note de-identification. |
| Outcome: | The proposed model can be transferred to a dataset with a limited number of labels, and improves on the state-of-the-art results on patient note de-identification. |
VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for document QA for visually rich documents outperform unimodal and long-context LLMs by 12-20%. |
| Approach: | They propose a multimodal Retrieval Augmented Generation approach that integrates visual and textual retrieval with linguistic reasoning. |
| Outcome: | The proposed approach outperforms unimodal and long-context LLM benchmarks for document QA by 12-20%. |
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current deep learning models fail to exploit syntactic information of sentences . proposed model incorporates syntax-based opinion possibility scores and syntaktic connections between the words . |
| Approach: | They propose to incorporate syntactic information of sentences into deep learning models for TOWE . they propose a novel regularization technique to improve the performance of the models . |
| Outcome: | The proposed model achieves state-of-the-art on four benchmark datasets. |
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages (2024.lrec-main)
Copied to clipboard
Thuat Nguyen, Chien Van Nguyen, Viet Dac Lai, Hieu Man, Nghia Trung Ngo, Franck Dernoncourt, Ryan A. Rossi, Thien Huu Nguyen
| Challenge: | Existing training datasets for large language models are often not fully disclosed. |
| Approach: | They propose a multilingual dataset with 6.3 trillion tokens in 167 languages . they use a pipeline of multiple stages to achieve the best quality for model training . |
| Outcome: | The proposed dataset is cleaned and deduplicated to achieve the best quality for model training . lack of transparency has hindered research on attributing and addressing hallucination and bias issues . 6.3 trillion tokens in 167 languages are used to train multilingual LLMs . |
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in natural language processing (NLP) have led to significant breakthroughs in the field. |
| Approach: | They evaluate ChatGPT over multiple tasks with diverse languages and large datasets to provide more comprehensive information for multilingual NLP applications. |
| Outcome: | The proposed model can process and generate texts for multiple languages due to its multilingual training data. |
Event Detection for Suicide Understanding (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for detecting suicide-related events are limited . recognizing suicide- related events is critical to understanding the condition, authors argue . |
| Approach: | They propose a dataset to detect event trigger words of suicide-related events in forums . they propose 'suicideED' dataset to capture suicidal actions and ideation . |
| Outcome: | The proposed dataset captures suicide actions and ideation, and general risk and protective factors. |
Scene Graph Modification Based on Natural Language Commands (2020.findings-emnlp)
Copied to clipboard
Xuanli He, Quan Hung Tran, Gholamreza Haffari, Walter Chang, Zhe Lin, Trung Bui, Franck Dernoncourt, Nhan Dam
| Challenge: | Numerous parsing methods have been developed for a single sentence, while a typical human-computer interaction session or conversation is not singleturn. |
| Approach: | They propose to modify an existing scene graph given a new user's command by using graph-based sparse transformer and cross attention information fusion to improve performance. |
| Outcome: | The proposed models outperform previous systems adapted from the machine translation and graph generation literature and contribute to the research community. |
Fine-grained Image Captioning with CLIP Reward (2022.findings-naacl)
Copied to clipboard
| Challenge: | Modern image captioning models are usually trained with text similarity objectives . reference captions often describe only the most salient objects in images . |
| Approach: | They propose to use CLIP to calculate multi-modal similarity and use it as a reward function . they propose a simple finetuning strategy to improve grammar that does not require extra text annotation. |
| Outcome: | The proposed model generates more distinctive captions than the CIDEroptimized model on text-to-image retrieval and fineCapEval. |
Fine-tuning CLIP Text Encoders with Two-step Paraphrasing (2024.findings-eacl)
Copied to clipboard
| Challenge: | Contrastive language-image pre-training models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval. |
| Approach: | They propose a fine-tuning approach to enhance the representations of CLIP models for paraphrases by leveraging large language models. |
| Outcome: | The proposed model improves on baseline models across paraphrased retrieval, visual genome relation and attribution, and seven semantic textual similarity tasks. |
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation (2020.findings-emnlp)
Copied to clipboard
Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Quan Hung Tran, Dejing Dou, Thien Huu Nguyen
| Challenge: | Aspect-based Sentiment Analysis (ABSA) seeks to predict sentiment polarity of input sentences toward a specific aspect. |
| Approach: | They propose a graph-based deep learning model that integrates dependency trees into deep learning models to improve ABSA performance. |
| Outcome: | The proposed model achieves state-of-the-art on three benchmark datasets. |
IGA: An Intent-Guided Authoring Assistant (2021.emnlp-main)
Copied to clipboard
Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer
| Challenge: | Pretrained language models have improved writing assistance functions such as autocomplete, but more complex and controllable writing assistants have yet to be explored. |
| Approach: | They build an intent-guided authoring assistant that follows fine-grained author directives by specifying different writing intents. |
| Outcome: | The proposed system generates output satisfying the author's intent and can be rephrased to their liking. |
MoDS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections (2025.naacl-long)
Copied to clipboard
Nishant Balepur, Alexa Siu, Nedim Lipka, Franck Dernoncourt, Tong Sun, Jordan Lee Boyd-Graber, Puneet Mathur
| Challenge: | Query-focused summarization (QFS) gives an overview of documents to answer a query, ignoring debatable ones. |
| Approach: | They propose a multi-LLM framework that uses a Query-focused summarization approach to create balanced summaries that answer debatable queries. |
| Outcome: | The proposed framework beats SOTA by 38-59% in topic paragraph coverage and balance, based on new citation metrics. |
BehanceQA: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts (2022.lrec-1)
Copied to clipboard
| Challenge: | Question-Answer (QA) is an effective method for storing knowledge . prior QA identification systems have been limited to formal written documents . a large-scale QA dataset annotated by human over 500 hours of video transcripts is a challenge . |
| Approach: | They present a large-scale QA identification dataset annotated by human over 500 hours of video transcripts. |
| Outcome: | The proposed dataset presents unique challenges for existing methods . it shows that the annotated dataset presents challenges for new methods - the results will be released . |
Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing datasets for event detection (ED) are limited to a small set of popular languages due to the high cost of data annotation. |
| Approach: | They propose a method to develop cross-lingual transfer learning models in high-resource source languages . they aim to transition the representations for target-language examples into the source-language space . |
| Outcome: | Extensive experiments over three languages demonstrate the state-of-the-art in CLTL. |
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for event coreference resolution use symbolic features, but they are noisy and contain errors. |
| Approach: | They propose a context-dependent gated module to adaptively control the information flows from the input symbolic features. |
| Outcome: | The proposed model achieves state-of-the-art on two datasets: ACE 2005 and KBP 2016 . |
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods struggle with content-style entanglement, leading to poor generalization across domains. |
| Approach: | They propose an explanation-by-design framework that explicitly disentangles style from content through architectural separation-by design. |
| Outcome: | The proposed framework disentangles style from content through architectural separation-by-design. |
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact (2026.eacl-long)
Copied to clipboard
Hyunji Lee, Seunghyun Yoon, Yunjae Won, Hanseok Oh, Geewook Kim, Trung Bui, Franck Dernoncourt, Elias Stengel-Eskin, Mohit Bansal, Minjoon Seo
| Challenge: | Prior work on instruction tuning datasets combined these data types without examining their distinct effects. |
| Approach: | They investigate how training LLMs with or without context affects model behavior and performance . they find that using context-augmented data as the backbone for vision-language models reduces hallucination . |
| Outcome: | The proposed training with context-augmented data reduces hallucination and improves grounding in the visual domain. |
Learning to Fuse Sentences with Transformers for Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive summarization systems that fuse sentences are not rewarded for correctly fusing sentences. |
| Approach: | They propose to leverage the knowledge of points of correspondence between sentences to enhance their ability to fuse sentences. |
| Outcome: | The proposed algorithms improve the ability of the proposed summarization systems to fuse sentences and show that they can fuse sentences in a way that retains the original meaning. |
GUI Agents: A Survey (2025.findings-acl)
Copied to clipboard
Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Jihyung Kil, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt
| Challenge: | Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life. |
| Approach: | They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities. |
| Outcome: | The proposed framework delineates their perception, reasoning, planning, and acting capabilities. |
Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering (2020.coling-main)
Copied to clipboard
| Challenge: | Interpretability and explainability of deep neural net models are always challenging due to their size and complexity. |
| Approach: | They propose to design an explainable, evidence-based memory network architecture that connects current sample with seen samples and bases its decision on these samples. |
| Outcome: | The proposed model can trace errors to training instances that might have caused errors . the proposed model achieves state-of-the-art performance on two popular datasets . |
SlimLM: An Efficient Small Language Model for On-Device Document Assistance (2025.acl-demo)
Copied to clipboard
| Challenge: | Small language models (SLMs) show promise for mobile deployment, but their real world performance and applications on smartphones remain understudied. |
| Approach: | They propose a slim language model with a model size of 125M to 8B and a context length of 8B for efficient on-device processing. |
| Outcome: | The proposed model is based on a Samsung Galaxy S24 and shows comparable or superior performance. |
ChartLens: Fine-grained Visual Attribution in Charts (2025.acl-long)
Copied to clipboard
| Challenge: | MLLMs suffer from hallucinations, where generated text fails to align with visual inputs. |
| Approach: | They propose a chart attribution algorithm that uses segmentation-based techniques to identify chart objects and employs set-of-marks prompting with MLLMs for fine-grained visual attribution. |
| Outcome: | The proposed algorithm improves fine-grained attributions by 26-66% . |
Demystifying the Power of Large Language Models in Graph Generation (2025.findings-naacl)
Copied to clipboard
Yu Wang, Ryan A. Rossi, Namyong Park, Nesreen K. Ahmed, Danai Koutra, Franck Dernoncourt, Tyler Derr
| Challenge: | Large Language Models (LLMs) have been used for graph discriminative tasks, but their potential for graph structure generation remains unexplored. |
| Approach: | They propose to use LLMs to generate graphs that optimize network properties by injecting domain expertise from network science into the code. |
| Outcome: | The proposed model generates graphs satisfying each property in different domains and compares it with established graph generative models across multiple domains. |
DocFin: Multimodal Financial Prediction and Bias Mitigation using Semi-structured Documents (2022.findings-emnlp)
Copied to clipboard
Puneet Mathur, Mihir Goyal, Ramit Sawhney, Ritik Mathur, Jochen Leidner, Franck Dernoncourt, Dinesh Manocha
| Challenge: | Existing research focuses on textual and audio modalities of financial disclosures but ignores the rich tabular data available in financial reports. |
| Approach: | They propose to combine tabular financial data with text transcripts and audio recordings to improve stock volatility and price movement prediction by 5-12% and reduce gender bias by over 30%. |
| Outcome: | The combined data improves stock volatility and price movement prediction by 5-12% and reduces gender bias caused due to audio-based neural networks by over 30%. |
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding (2021.acl-long)
Copied to clipboard
Khalil Mrini, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole
| Challenge: | Existing methods for medical question understanding often fail to provide high recall in answer retrieval. |
| Approach: | They propose a multi-task learning method with data augmentation for medical question understanding that uses just one dataset to optimize for both tasks. |
| Outcome: | The proposed method outperforms existing MTL methods across 4 datasets of medical question pairs in ROUGE scores, RQE accuracy and human evaluation. |
Exploiting the Syntax-Model Consistency for Neural Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing deep learning models for Relation Extraction (RE) have limited generalization beyond the syntactic structures of the input sentences. |
| Approach: | They propose a deep learning model that uses dependency trees to extract syntactic importance of words for Relation Extraction. |
| Outcome: | The proposed model outperforms existing models on three RE benchmark datasets. |
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. |
| Approach: | They propose a Variational Hierarchical Dialog Autoencoder for modeling the complete aspects of goal-oriented dialogs using inter-connected latent variables and learns to generate coherent dialogs from the latent spaces. |
| Outcome: | The proposed model outperforms previous strong baselines on dialog response generation and user simulation tasks. |
On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning (D19-62)
Copied to clipboard
| Challenge: | Existing models for relation extraction use different pooling mechanisms to perform pooling for RE. |
| Approach: | They conduct a comprehensive study to evaluate the effectiveness of different pooling mechanisms for deep learning in biomedical RE. |
| Outcome: | The proposed model outperforms the previous models on two biomedical datasets. |
Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 Training (2023.findings-acl)
Copied to clipboard
| Challenge: | Relation Extraction (RE) is the task of identifying semantic relation between entities mentioned in text. |
| Approach: | They propose a framework to automatically generate labeled data for Relation Extraction . they propose 'reward function' to update pre-trained language model for RE . |
| Outcome: | The proposed framework generates labeled data for relation extraction using a pre-trained language model and a meta learning approach to improve the generated samples. |
A Web-based Framework for Collecting and Assessing Highlighted Sentences in a Document (C18-2)
Copied to clipboard
| Challenge: | Existing automated summarization techniques are not fully mature, authors say . existing frameworks focus on summarizing text, but highlight is not always accurate . |
| Approach: | They propose a web-based framework to efficiently and scalably crowdsource two tasks . they aim to collect highlight annotations and compare the performance of automated highlighting systems . |
| Outcome: | The proposed framework can crowdsource two tasks to identify key portions of a document that are the most important to a reader. |
MeetingBank: A Benchmark Dataset for Meeting Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | a lack of annotated meeting corpora hinders the development of meeting summarization technology. |
| Approach: | They present a new benchmark dataset of city council meetings over the past decade . they use a divide-and-conquer approach to divide professionally written minutes into shorter passages . |
| Outcome: | The proposed dataset provides a testbed for various meeting summarization systems and allows the public to gain insight into how council decisions are made. |
Offensive Content Detection via Synthetic Code-Switched Text (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to detect offensive content in social media platforms are limited by the availability of labeled code-switched data. |
| Approach: | They propose a method for generating synthetic code-switched offensive content data using human-generated data and a keyword classification baseline. |
| Outcome: | The proposed algorithm can be used to generate synthetic code-switched offensive content data and train it on human-generated data. |
QACE: Asking Questions to Evaluate an Image Caption (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing metric for image captioning evaluation is based on n-gram similarity metrics but these fail to capture semantic errors in captions. |
| Approach: | They propose a new metric based on Question Answering for Caption Evaluation to evaluate image captioning based upon Question Generation and Question Answers systems. |
| Outcome: | The proposed metric is multi-modal, reference-less and explainable. |
X-METRA-ADA: Cross-lingual Meta-Transfer learning Adaptation to Natural Language Understanding and Question Answering (2021.naacl-main)
Copied to clipboard
| Challenge: | Multilingual models have gained popularity for their zero-shot cross-lingual transfer learning capabilities, but their generalization ability is inconsistent for typologically diverse languages. |
| Approach: | They propose a meta-learning approach that adapts MAML to learn to adapt to new languages . they extensively evaluate two cross-lingual NLU tasks using English as source and spanish as target . |
| Outcome: | The proposed approach outperforms naive fine-tuning on cross-lingual tasks for most languages. |