South NLP
Symposium 2024

Reception

If you are registered, please take your name tags from the registration desk. Onsite registration is not available. Coffee and tea are available nearby.

Opening Ceremony

Organizing Committee

Keynote Speech 1: Kathleen McKeown

Session Chair: Xuan Wang

Addressing Large Language Models that Lie: Case Studies in Summarization (slides)

Break

Poster presenters should be prepared for the upcoming session. Coffee and tea are available.

Poster Presentations 1

Presenters are denoted by an asterisk (*)

1. How Misogynistic is Rap? Lyrical and Comparative Analysis of Misogyny in Rap Music - Michael Cao, Michael Wang*, Indy Gu (poster)
2. War of Words: Using Large Language Models and Retrieval Augmented Generation to Classify, Counter and Diffuse Hate Speech - Rohan Singh Leekha*, Olga Simek, Charlie K. Dagli(poster)
3. NLP Analysis of Inaugural and State of the Union Discourse - Kevin Huang, Shuyang Bian* (poster)
4. MATHWELL: Generating Educational Math Word Problems at Scale - Bryan R. Christ*, Jonathan Kropko, Thomas Hartvigsen (poster)
5. Meta-Tuning LLMs to Elicit Lexical Knowledge of Language Style - Ruohao Guo*, Wei Xu, Alan Ritter (poster)
6. Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies - Junlin Wang*, Siddhartha Jain, Ben Athiwaratkun, Dejiao Zhang, Baishakhi Ray, Varun Kumar (poster)
7. LLMs as Zero-Shot Multi-Label Classifiers for Bangla Documents - Souvika Sarkar*, Shubhra Kanti Karmaker Santu (poster)
8. Having Beer after Prayer? Measuring Cultural Bias in Large Language Models - Tarek Naous*, Michael J. Ryan, Alan Ritter, Wei Xu (poster)
9. Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection - Min Zhang, Jianfeng He, Taoran Ji, Czhang-Tien Lu
10. Quality Assessment of Open-Source Language Model Generated Sentence Pairs in Rotorcraft Aviation Domain - Emma L. McDaniel*, Alicia I. Ruvinsky (poster)
11. Benchmarking LLMs on the Semantic Overlap Summarization Task - John Salvador*, Naman Bansal, Mousumi Akter, Souvika Sarkar, Anupam Das, Shubhra Kanti Karmaker Santu (poster)
12. Ontology Learning System (OLS) - Sundos Al Subhi*, Chetan Tiwari, Armin R. Mikler (poster)
13. Benchmarking LLMs on Extracting Polymer Nanocomposite Samples - Ghazal Khalighinejad*, Defne Circi, Cate Brinson, Bhuwan Dhingra (poster)
14. ExSiM: Explainable Methodology to Upgrade Sentence Similarity Metrics to Document-Level - Matthew C. Williams Jr.*, Shubhra Kanti Karmaker Santu (poster)
15. Word Embeddings Revisited: Do LLMs Offer Something New? - Matthew Freestone*, Shubhra Kanti Karmaker Santu (poster)
16. Self-Specialization: Uncovering Latent Expertise within Large Language Models - Junmo Kang*, Hongyin Luo, Yada Zhu, James R. Glass, David D. Cox, Alan Ritter, Rogerio Feris, Leonid Karlinsky (poster)
17. Constrained Decoding for Cross-lingual Label Projection - Duong Minh Le*, Yang Chen, Alan Ritter, Wei Xu (poster)
18. Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions? - Yang Chen*, Hexiang Hu, Yi Luan, Haitian Sun, Soravit Changpinyo, Alan Ritter, Ming-Wei Chang (poster)
19. Navigational and Spatial Expressions in Natural Language : An Analysis - Kourosh T. Baghaei*, Antonios Anastasopoulos, Dieter Pfoser (poster)
20. Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning - Zhiyang Xu, Ying Shen*, Trevor Ashby, Lifu Huang
21. Improving Contextual Congruence Across Modalities for Effective Multimodal Marketing using Knowledge-infused Learning - Trilok Padhi, Ugur Kursuncu*, Yaman K. Singla, Valerie L. Shalin, Lane Peterson Fronczek (poster)
22. FlowGPT: How Long can LLMs Trace Back and Predict the Trends of Graph Dynamics? - Zijian Zhang, Zonghan Zhang, Zhiqian Chen* (poster)
23. Supporting Research through WebMap – Multifaceted Semantic Link Induction in the Web - Mario M. Kubek*, Georg Philipp Roßrucker (poster)
24. Revolutionizing Administrative Tasks: Emora Assistant Bot - Ellie S. Paek*, Talyn Fan, Jinho D. Choi (poster)
25. Emory Infobot: A LLM-powered Virtual Assistant for University Students - Darren Ni*, Aaron Zaiman, Yutong Hu, Jinho D. Choi (poster)
26. Scalable Classification of Online Vaccine Concerns - Rickard Stureborg*, Chloe Zhu, Christopher Li, Bhuwan Dhingra (poster)
27. ChatShop: Interactive Information Seeking with Language Agents - Sanxing Chen*, Sam Wiseman, Bhuwan Dhingra (poster)
28. TAGMI - A Taxonomy for Artificial General Machine Intelligence - R. Alexander Knipper*, Charles S. Knipper, Shubhra Kanti Karmaker Santu (poster)
29. Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation - David Heineman*, Yao Dou, Wei Xu (poster)
30. Quantifying Perceived Distance between Spatial Entities in Literary Text - Rosie Larson*, Sandeep Soni (poster)
31. Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA - David Heineman, Yao Dou*, Mounica Maddela, Wei Xu (poster)
32. Conversational Equations: A Conversational Question-Answering Dataset Grounded in Scientific Equations - Anirudh S. Sundar*, Shaleen Parikh, Larry Heck (poster)
33. ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI - Sarah E. Finch*, Jinho D. Choi (poster)
34. Aspect-Oriented Sentiment Analysis For Airlines - Lakshmi Priya Irava*, Mario M. Kubek (poster)
70. Unlocking the Potential of Single-Cell Multi-Omics Data with Large-Scale Pre-Trained Transformer Models - Sajib Acharjee Dip, Sindhura Kommu, Xuan Wang (poster)

Lunch Buffet

Lunch is provided for registerred attendees. Oral presenters should be prepared for the upcoming session.

Oral Presentations 1

Session Chair: Sandeep Soni
Presenters are denoted by an asterisk (*)

1. Perceptions of Language Technology Failures from South Asian English Speakers - Faye Holt*, William B. Held, Diyi Yang (slides)
2. Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models - Zihao Lin*, Mohammad Beigi, Lifu Huang (slides)
3. The Daunting Dilemma with Sentence Encoders: Glowing on Standard Benchmarks, Struggling with Capturing Basic Semantic Properties - Yash mahajan*, Naman Bansal, Shubhra Kanti Karmaker ("Santu") (slides)
4. Distinguishing PTSD from Anxiety Disorders: A Machine Learning Investigation of Linguistic Patterns in Online Mental Health Communities - Youngmeen Kim* (slides)

Keynote Speech 2: Mohit Bansal

Session Chair: Lifu Huang

Multimodal Generative LLMs: Unification, Interpretability, Evaluation (slides)

Break

Poster presenters should be prepared for the upcoming session. Coffee and tea are available.

Poster Presentations 2

Presenters are denoted by an asterisk (*)

35. Reducing Privacy Risks in Online Self-Disclosures with Language Models - Yao Dou*, Isadora Krsek, Tarek Naous, Anubha Kabra, Sauvik Das, Alan Ritter, Wei Xu (poster)
36. Global Gallery: The Fine Art of Painting Culture Portraits through Multilingual Instruction Tuning - Anjishnu Mukherjee*, Aylin Caliskan, Ziwei Zhu, Antonios Anastasopoulos (poster)
37. Stanceosaurus 2.0: Classifying Stance Towards Multicultural Misinformation - Jonathan Zheng, Anton Lavrouk, Tarek Naous*, Ashutosh Baheti, Ian Ligon, Alan Ritter, Wei Xu (poster)
38. REALITY: Empowering Religious Dialogue - A Chatbot Trained on Religious Texts for User Inquiry - Jacob Choi*, Jinho D. Choi (poster)
39. The Co-Evolving Signs of the Anti-Kremlin Rhetoric: A Longitudinal Analysis of Offline and Online Indicators from Russian Opposition Telegram Channels - Apaar Bawa*, Ugur Kursuncu, Dilshod Achilov, Valerie Shalin (poster)
40. College Web-Application Large Language Model - Noah Sturgill* (poster)
41. Russia is not Putin: Collocational analyses of “Russia,” “Russians,” and “Putin” in US Mass Media - Ulbossyn Parmanova* (poster)
42. Limitations of Large Language Models as Automatic Evaluators - Rickard Stureborg*, Dimitris Alikaniotis, Yoshi Suhara (poster)
43. ReGAL: Refactoring Programs to Discover Generalizable Abstractions - Elias Stengel-Eskin, Archiki Prasad*, Mohit Bansal
44. Semantic Overlap Summarization using Sentence Autoencoders - Naman Bansal*, John Salvador, Shubhra Kanti Karmaker Santu (poster)
45. Using Large Language Models for Data Extraction from Tables in Materials Literature - Defne Circi*, Ghazal Khalighinejad, Bhuwan Dhingra, L. Brinson (poster)
46. Retrieval-Augmented Generation: Is Dense Passage Retrieval Retrieving? - Benjamin Reichman*, Larry Heck (poster)
47. Log probability scores provide a closer match to human plausibility judgments than prompt-based evaluations - Anna A. Ivanova*, Aalok Sathe, Ben Lipkin, Evelina Fedorenko, Jacob Andreas (poster)
48. PruFed: Federated Fine-Tuning of Pruned LLMs - Shrenik Bhansali*, Alwin Jin, Tyler Lizzo, Larry Heck (poster)
49. Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning - Murong Yue*, Jie Zhao, Min Zhang, Liang Du, Ziyu Yao (poster)
50. LLMs as On-demand Customizable Service - Souvika Sarkar*, Mohammad Fakhruddin Babar, Monowar Hasan, Shubhra Kanti Karmaker Santu (poster)
51. Script-Agnostic Language Identficiation - Milind Agarwal*, Joshua Otten, Antonios Anastasopoulos (poster)
52. Monolingual and Bilingual Language Acquisition in Language Models - Mihir Sharma*, Ryan Ding, Raj Sanjay Shah, Sashank Varma (poster)
53. Semantic-Aware Text-Based Speaker Diarization: Leveraging Language Models for Sentence-Level Speaker Change Detection - Peilin Wu*, Jinho D. Choi (poster)
54. CREMA: Multimodal Compositional Video Reasoning via Efficient Modular Adaptation and Fusion - Shoubin Yu*, Jaehong Yoon, Mohit Bansal
55. Conversational Gestures: Transforming Text into Full-Body Virtual Interactions - Saif Punjwani*, Bowen Zuo, Micah Grimes, Larry Heck (poster)
56. Parallel Multilingual Pre-Training for Multi-Modal Representations - Nathaniel Krasner*, Nicholas Lanuzo (poster)
57. Decoding the Chinese Government Work Report: A Natural Language Processing Approach - Shuyang Bian*, Roberto Franzosi
58. Refined Datasets for Competence-Level Classification and Resume & Job Matching - Boxin Zhao*, Jinho D. Choi (poster)
59. Analyzing Brain Age through Entity-Centric Analysis of Narratives in Picture Description Tasks - Benjamin Ascoli*, Ezequiel Gleichgerrcht, Jinho D. Choi (poster)
60. Automating PTSD Diagnostics in Clinical Interviews: Leveraging Large Language Models for Trauma Assessments - Sichang Tu*, Abigail Powers, Natalie Merrill, Negar Fani, Sierra Carter, Stephen Doogan, Jinho D. Choi (poster)
61. Large Language Models as your Personal Data Scientist - Md. Mahadi Hassan*, R. Alexander Knipper, Shubhra Kanti Karmaker Santu (poster)
62. Conversational Figures: A Conversational Question-Answering Dataset Grounded in Scientific Figures and Text - Anirudh S Sundar*, William Gay, Antonia Rabisheva, Larry Heck (poster)
63. Universal Multi-Dimensional Text Evaluation Enhanced with Auxiliary Evaluation Aspects - Minqian Liu*, Ying Shen, Zhiyang Xu, Lifu Huang (poster)
64. SubjECTive-QA: A dataset for the qualitative evaluation of answers in Earnings Call Transcripts (ECTs) - Huzaifa Pardawala*, Veer Kejriwal, Siddhant Sukhani, Abhishek Pillai, Rohan Bhasin, Dhruv Adha, Tarun Mandapati, Andrew DiBiasio, Agam Shah, Sudheer Chava (poster)
65. MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models - Justin Chen*, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal (poster)
66. EMONA: Moral Opinions towards Events in News Articles - Yuanyuan Lei*, Md Messal Monem Miah, Ayesha Qamar, Sai Ramana Reddy, Jonathan Tong, Haotian Xu, Ruihong Huang (poster)
67. Modeling Bias in Automatic Speech Recognition - Camille Harris*, Chijioke Mgbahurike, Diyi Yang (poster)
68. Noun phrase complexity analyzer (NPCA) - Soyeon Sim* (poster)
69. Tree- or Chain-of-Thought? Exploring Complex Reasoning in Multi-Hop Question Answering - Zhenyu Bi*, Daniel Hajialigol, Priya Pitre, Zhongkai Sun, Jie Hao, Xuan Wang (poster)

Break

Oral presenters should be prepared for the upcoming session.

Oral Presentations 2

Session Chair: Wei Xu
Presenters are denoted by an asterisk (*)

5. Dialogue State Generation: Transcending Slot Schemas for Domain-General State Inference - James D. Finch*, Boxin Zhao, Jinho D. Choi (slides)
6. VideoDirectorGPT: Consistent Multi-Scene Video Generation via LLM-Guided Planning - Han Lin*, Abhay Zala, Jaemin Cho, Mohit Bansal (slides)
7. Atomic Self-Consistency for Better Long Form Generations - Raghuveer Thirukovalluru*, Yukun Huang, Bhuwan Dhingra (slides)
8. A Psychological View to Social Bias in LLMs: Evaluation and Mitigation - Chahat Raj*, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu (slides)

Closing Ceremony

General Chair