Papers with visualizations
NLP+Vis: NLP Meets Visualization (2023.emnlp-tutorial)
Copied to clipboard
| Challenge: | This tutorial will introduce NLP+Vis with a focus on two main threads of work: NLP for Vis and Vis for NLP. |
| Approach: | tutorial will introduce NLP+Vis with a focus on two main threads of work . overview of research topics on combining NLP and Vis techniques will be covered . |
| Outcome: | The tutorial will introduce NLP+Vis with a focus on two main threads of work . it will provide an overview of research topics on combining NLP and Vis techniques . |
Writing Code for NLP Research (D18-3)
Copied to clipboard
| Challenge: | upcoming workshop on open source software for NLP aims to share best practices for writing code for Nl research . participants will learn how to write research code that facilitates good science and easy experimentation . |
| Approach: | this tutorial aims to share best practices for writing code for NLP research . participants will learn how to write research code that facilitates good science and easy debugging . |
| Outcome: | the workshop on open source software for NLP aims to share best practices for writing code for Nl research . participants will learn how to write research code that facilitates good science and easy experimentation . |
AnEMIC: A Framework for Benchmarking ICD Coding Models (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Diagnostic coding is the task of assigning diagnosis codes defined by the ICD (International Classification of Diseases) standard to patient visits based on clinical notes. |
| Approach: | They propose to use an ICD coding framework to train and benchmark models . they correct errors in preprocessing and provide an interactive demo to analyze the models based on custom inputs. |
| Outcome: | The framework corrects errors in preprocessing and provides key models and weights trained on correctly preprocessed datasets. |
Game-Based Video-Context Dialogue (D18-1)
Copied to clipboard
| Challenge: | Current dialogue systems focus more on textual and speech context knowledge and are usually based on two speakers. |
| Approach: | They propose to use live soccer game videos and Twitch.tv chats to develop visual-grounded dialogue models. |
| Outcome: | The proposed model can generate relevant temporal and spatial event language from live video and chat history while also being relevant to chat history. |
The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces (2026.acl-srw)
Copied to clipboard
Angelina Tsai, Shreya Subramanian, Catherine Liu, Kimberly Lopez, Leif Zinn-Brooks, Alexia E. Schulz, Adaku Uchendu
| Challenge: | Large Language Models (LLMs) have unprecedented capabilities, but they pose security concerns . current adversarial attacks exploit vulnerabilities in the embedding space of language models, allowing attackers to bypass safety guardrails and cause significant harmful consequences. |
| Approach: | They propose to use topological data analysis to characterize how adversarial perturbations act on text inputs by computing persistent homology metrics from attention maps across different model architectures. |
| Outcome: | The proposed visualizations show that adversarial perturbations alter higher-dimensional topological features in ways that distinguish them from clean, non-adversarial inputs. |
Dialz: A Python Toolkit for Steering Vectors (2025.acl-demo)
Copied to clipboard
| Challenge: | *Dialz* is a Python library for advancing research on steering vectors for open-source LMs. |
| Approach: | They propose a Python library for advancing research on steering vectors for open-source LMs. |
| Outcome: | The proposed method reduces harmful outputs and provides insights into model behaviour across different layers. |
Riveter: Measuring Power and Social Dynamics Between Entities (2023.acl-demo)
Copied to clipboard
| Challenge: | Riveter provides a complete pipeline for analyzing verb connotations associated with entities in text corpora. |
| Approach: | et al., 2005, provide a verb-centric analysis pipeline for verb connotations in text corpora . they prepopulate the pipeline with connotation frames of sentiment, power, and agency . lexical frameworks have been foundational tools in social science, digital humanities, and natural language processing . |
| Outcome: | Riveter provides a complete pipeline for analyzing verb connotations associated with entities in text corpora. |
Quest2DataAgent: Automating End-to-End Scientific Data Collection (2025.emnlp-demos)
Copied to clipboard
Tianyu Yang, Yuhan Liu, Sobin Alosious, Ethan A. Brown, Jason R. Rohr, Tengfei Luo, Xiangliang Zhang
| Challenge: | Existing approaches for data collection are labor-intensive and dependent on domain expertise. |
| Approach: | They propose a general-purpose multi-agent framework for automating scientific data collection workflows. |
| Outcome: | The proposed framework improves data relevance, usability, and time efficiency over existing methods. |
Speaker-change Aware CRF for Dialogue Act Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. |
| Approach: | They propose to modify the CRF layer to take speaker-change into account and learn meaningful transition patterns conditioned on speaker-changing DA labels. |
| Outcome: | The proposed model outperforms the original model with wide margins for some DA labels. |
Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization (2020.lrec-1)
Copied to clipboard
| Challenge: | a new corpus of conversations is being developed to support data visualization exploration . we use data augmentation to improve our methods for dialogue act classification . |
| Approach: | They propose to use a corpus of conversations to annotate contextualized dialogue acts . they highlight how thinking aloud affects interpretation of dialogue acts in the context . |
| Outcome: | The proposed AI can support visualization exploration with a small corpus of conversations . the proposed AI outperforms existing models in terms of performance and performance . |
The CLAMS Platform at Work: Processing Audiovisual Data from the American Archive of Public Broadcasting (2022.lrec-1)
Copied to clipboard
| Challenge: | The Computational Linguistics Applications for Multimedia Services (CLAMS) platform provides access to computational content analysis tools for multimedia material. |
| Approach: | They describe the CLAMS platform as it is and its initial prototype implementation from 2019 . they use a common multi-modal representation language called MMIF to create a workflow . |
| Outcome: | The CLAMS platform is a new version of an initial prototype from 2019 . it can be used to add metadata to mass-digitized multimedia collections . the proposed version is based on the American Archive of Public Broadcasting data . |
Enough Coin Flips Can Make LLMs Act Bayesian (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models exhibit the ability to generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning. |
| Approach: | They investigate whether large language models use in-context learning to generalize given few-shot examples in their input prompt. |
| Outcome: | The proposed model can generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning. |
When and how to paraphrase for named entity recognition? (2023.acl-long)
Copied to clipboard
Saket Sharma, Aviral Joshi, Yiyun Zhao, Namrata Mukhija, Hanoz Bhathena, Prateek Singh, Sashank Santhanam
| Challenge: | Named entity recognition (NER) is a key component underpinning many industrial pipelines for a variety of downstream applications. |
| Approach: | They propose to use back translation to annotate entity spans in generations and propose a paraphraser with a larger dataset. |
| Outcome: | The proposed method improves NER performance across different datasets with gold annotations and paraphrasing strength. |
Is this chart lying to me? Automating the detection of misleading visualizations (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has shown that both humans and MLLMs are frequently deceived by misleading visualizations. |
| Approach: | They propose a benchmark of 2,604 real-world visualizations annotated with 12 types of misleaders. |
| Outcome: | The proposed framework can detect misleading visualizations and identify specific design rules they violate . the proposed framework is based on a synthetic dataset of 81,814 visualizations . |
Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on human judgment to assess data accuracy and visual communication, which is costly and unscalable. |
| Approach: | They propose a framework that leverages Visual Question Answering (VQA) models to automate the evaluation of LLM-generated data visualizations. |
| Outcome: | The proposed framework assesses data representation quality and communicative clarity of charts using two leading VQA benchmark datasets, ChartQA and PlotQA, with visualizations generated by OpenAI’s GPT-3.5 Turbo and Meta’s Llama 3.1 70B-Instruct models. |
Revisiting the Importance of Encoding Logic Rules in Sentiment Classification (D18-1)
Copied to clipboard
| Challenge: | Neural models that explicitly encode word order, syntax and semantic features are unequipped to deal with complex syntactic structures that affect sentiment, such as contrastive conjunctions. |
| Approach: | They propose to use contextualized ELMo embeddings instead of logic rules to compare models on syntactically complex sentences. |
| Outcome: | The proposed models outperform baseline models even on sentences with ambiguous sentiment labels. |
Evaluating Topic Model on Asymmetric and Multi-Domain Financial Corpus (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent research attempts to quantify the exposure of market assets to various risks from text and how assets react if the risk materializes itself. |
| Approach: | They propose two new metrics to evaluate the behavior of different types of topic models with respect to pitfalls previously mentioned about document risk distribution extraction. |
| Outcome: | The proposed models can be used to extract unbiased risk information from financial domain data and correct coherence imbalances. |
Mere Contrastive Learning for Cross-Domain Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to cross-domain sentiment analysis are labor-intensive and time-consuming. |
| Approach: | They propose a modified contrastive objective with in-batch negative samples to allow sentence representations from the same class to be pushed closer while those from the different classes become further apart in the latent space. |
| Outcome: | The proposed model can achieve state-of-the-art in cross-domain and multi-domain sentiment analysis tasks while transferring knowledge learned in the source domain to the target domain. |
Investigating the Helpfulness of Word-Level Quality Estimation for Post-Editing Machine Translation Output (2021.emnlp-main)
Copied to clipboard
| Challenge: | Post-editing (PE) machine translation (MT) output can save time and reduce errors. |
| Approach: | They propose to use automatic word-level quality estimation to predict correctness of MT output to flag problematic output. |
| Outcome: | The proposed model is not good enough to support human translations, but is based on a visualization reflecting uncertainty of the model. |
When Truthful Representations Flip Under Deceptive Instructions? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. |
| Approach: | They use Sparse Autoencoders to analyze LLM's internal representations to determine when and how they "flip" from truthful to deceptive under deceptively crafted instructions. |
| Outcome: | The proposed model's True/False output is predictable across all conditions based on the model''s representation, and the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations. |
Improving Multimodal Sentiment Analysis: Supervised Angular margin-based Contrastive Learning for Enhanced Fusion Representation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for multimodal sentiment analysis focus on forming positive and negative pairs, neglecting the variation in sentiment scores within the same class. |
| Approach: | They propose a framework to enhance discrimination and generalizability of the multimodal representation and overcome biases in the fusion vector’s modality. |
| Outcome: | The proposed model improves discrimination and generalizability of the multimodal representation and overcomes biases in the fusion vector’s modality. |
Do It Yourself (DIY): Modifying Images for Poems in a Zero-Shot Setting Using Weighted Prompt Manipulation (2025.emnlp-main)
Copied to clipboard
| Challenge: | a novel method to enhance imagery in poetic language is proposed . weighted prompt manipulation is a new approach to enhance poetry images . current diffusion models struggle to interpret metaphorical language, symbolism, and nuanced themes. |
| Approach: | They propose a weighted prompt manipulation technique that modifies attention weights and text embeddings within diffusion models to enhance or suppress specific words' influence in the final generated image. |
| Outcome: | The proposed technique enhances or suppresses the influence of specific words in the final generated image, leading to semantically richer and more contextually accurate visualizations. |
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Data-driven storytelling uses visual aids and visualizations to convey insights. |
| Approach: | They propose a task for data story generation using large language models and a benchmark containing 1,449 stories from diverse sources. |
| Outcome: | The proposed framework outperforms non-agentic counterparts in both model-based and human evaluations, but also reveals unique challenges in data story generation. |
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections (2026.findings-acl)
Copied to clipboard
| Challenge: | Several studies rely on additional models to optimize mixtures. |
| Approach: | They propose a method that dynamically optimizes instruction-tuning dataset mixtures by prior-scaled Boltzmann Exploration and a multi-armed bandit setup. |
| Outcome: | The proposed method improves the TÜLU-2-mixture and TÜLO-3-mixtures across 10 benchmarks while introducing minimal computational overhead over naive sampling. |