LTI Authors Feature Prominently at EMNLP

32 papers from LTI researchers featured at this year's conference

The LTI is well-represented at this year's Conference on Empirical Methods in Natural Language Processing (EMNLP), with 32 papers from LTI authors accepted.

The conference, which bills itself as "one of the most prominent conferences in the field of Natural Language Processing," takes place November 12 through 16 in a hybrid format, with in-person events in Miami, Florida. This year's EMNLP, the conference's 29th edition, received an unprecedented number of paper submissions: 6,395, according to conference organizers.

The full list of accepted papers from LTI researchers, including days and times of presentations, is as follows (LTI authors in bold):

November 12 (Tuesday)

1. ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?
   • Link to Paper
   • Authors: Siddhant Waghjale, Vishruth Veerendranath, Zora Zhiruo Wang, Daniel Fried
   • Presentation Type: Poster
   • Session: NLP Applications 1, Session 02, 11:00-12:30
2. Dense X Retrieval: What Retrieval Granularity Should We Use?
   • Link to Paper
   • Authors: Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Dong Yu, Hongming Zhang
   • Presentation Type: Poster
   • Session: Information Retrieval and Text Mining 1, Session 02, 11:00-12:30
3. A Survey on In-context Learning
   
   • Link to Paper
   • Authors: Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, Zhifang Sui
   • Presentation Type: Poster
   • Session: Language Modeling 2, Session 03, 14:00-15:30
4. GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text
   • Link to Paper
   • Authors: Michael Ginn*, Lindia Tjuatja*, Taiqi He, Enora Rice, Graham Neubig, Alexis Palmer, Lori Levin
   • Presentation Type: Poster
   • Session: Multilinguality and Language Diversity 1, Session 03, 14:00-15:30
5. HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs
   • Link to Paper
   • LTI Authors: Jocelyn Shen, Joel Mire, Hae Won Park, Cynthia Breazeal & Maarten Sap
   • Presentation Type: Oral
   • Session: Computational Social Science and Cultural Analytics 1, Session 03, 14:00-15:30
6. Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages?
   • Link to Paper
   • Authors: Jimin Sohn, Haeji Jung, Alex Cheng, Jooeon Kang, Yilin Du, David Mortensen
   • Presentation Type: Poster
   • Session: Discourse + Phonology + Syntax 1, Session 03, 14:00-15:30
7. Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
   • Link to Paper
   • Authors: Seungone Kim, Juyoung Suk, Shayne Longpre, Bill Yuchen Lin, Jamin Shin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, Minjoon Seo
   • Presentation Type: Poster
   • Session: Resources and Evaluation 2, Session 04, 16:00-17:30
8. RAGViz: Diagnose and Visualize Retrieval-Augmented Generation
   • Link to Paper
   • Authors: Tevin Wang, Jingyuan He, Chenyan Xiong
   • Presentation Type: Demo
   • Session: Demo, Session 04, 16:00-17:30

1. Towards Robust Speech Representation Learning for Thousands of Languages
   • Link to Paper
   • Authors: William Chen, Wangyou Zhang, Yifan Peng, Xinjian Li, Jinchuan Tian, Jiatong Shi, Xuankai Chang, Soumi Maiti, Karen Livescu, Shinji Watanabe
   • Presentation Type: Poster
   • Session: Speech Processing and Spoken Language Understanding 1, Session 06, 10:30-12:00
2. SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM
   
   • Link to Paper
   • Authors: Jielin Qiu, Andrea Madotto, Zhaojiang Lin, Paul A. Crook, Yifan Ethan Xu, Xin Luna Dong, Christos Faloutsos, Lei Li, Babak Damavandi, Seungwhan Moon
   • Presentation Type: Poster
   • Session: Resources and Evaluation 3, Session 06, 10:30-12:00
3. Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems
   
   • Link to Paper
   • Authors: Chinmay Dandekar, Wenda Xu, Xi Xu, Siqi Ouyang, Lei Li
   • Presentation Type: Demo
   • Session: Demo, Session 06, 10:30-12:00
4. Learning Personalized Alignment for Evaluating Open-ended Text Generation
   
   • Link to Paper
   • Authors: Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian
   • Presentation Type: Poster
   • Session: Resources and Evaluation 3, Session 06, 10:30-12:00
5. MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
   
   • Link to Paper
   • Authors: Weiwei Sun, Zhengliang Shi, Jiulong Wu, Lingyong Yan, Xinyu Ma, Yiding Liu, Min Cao, Dawei Yin, Zhaochun Ren
   • Presentation Type: Poster
   • Session: Resources and Evaluation 3, Session 06, 10:30-12:00
6. Is This the Real Life? Is This Just Fantasy? The Misleading Success of Simulating Social Interactions With LLM
   • Link to Paper
   • Authors: Xuhui Zhou, Zhe Su, Tiwalayo Eisape, Hyunwoo Kim & Maarten Sap
   • Presentation Type: Poster
   • Session: Resources and Evaluation 3, Session 06, 10:30-12:00
7. Implicit Personalization in Language Models: A Systematic Study
   • Link to Paper
   • Authors: Zhijing Jin, Nils Heil, Jiarui Liu, Shehzaad Dhuliawala, Yahang Qi, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan
   • Presentation Type: Poster
   • Session: Human-centered NLP 2, Session 06, 10:30-12:00
8. Evaluating the Effectiveness of Large Language Models in Establishing Conversational Grounding
   • Link to Paper
   • Authors: Biswesh Mohapatra, Manav Nitin Kapadnis, Laurent Romary, Justine Cassell
   • Presentation Type: Poster
   • Session: Dialogue and Interactive Systems 2, Session 09, 16:00-17:30
9. Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions
   
   • Link to Paper
   • Authors: Leena Mathur, Paul Pu Liang, Louis-Philippe Morency
   • Presentation Type: Poster
   • Session: Multimodality and Language Grounding to Vision, Robotics and Beyond 4 , Session 09, 16:00-17:30
10. LumberChunker: Long-Form Narrative Document Segmentation
    
    • Link to Paper
    • Authors: André V. Duarte, João DS Marques, Miguel Graça, Miguel Freire, Lei Li, Arlindo L. Oliveira
    • Presentation Type: Poster
    • Session: Information Retrieval and TextMining 3, Session 09, 16:00-17:30
11. Tools Fail: Detecting Silent Errors in Faulty Tools
    
    • Link to Paper
    • Authors: Jimin Sun, So Yeon Min, Yingshan Chang, Yonatan Bisk
    • Presentation Type: Poster
    • Session: Language Modeling 3, Session 09, 16:00-17:30
12. Do LLMs Exhibit Human-like Response Biases? A Case Study in Survey Design
    • Link to Paper
    • Authors: Lindia Tjuatja*, Valerie Chen*, Tongshuang Wu, Ameet Talwalkar, Graham Neubig
    • Presentation Type: Poster
    • Session: TACL + CL, Session 09, 16:00-17:30
13. An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance
    • Link to Paper
    • Authors: Simran Khanuja, Sathyanarayanan Ramamoorthy, Yueqi Song, Graham Neubig
    • Presentation Type: Oral
    • Session: Resources and Evaluation 4, Session 09, 16:00-17:30

1. The Empirical Variability of Narrative Perceptions of Social Media Texts
   • Link to Paper
   • Authors: Joel Mire, Maria Antoniak, Elliott Ash, Andrew Piper & Maarten Sap
   • Presentation Type: Oral
   • Session: Computational Social Science and Cultural Analytics 3, Session 11, 10:30-12:00
2. Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
   • Link to Paper
   • Authors: Hyungjoo Chae, Yeonghyeon Kim, Seungone Kim, Kai Ong, Beong-woo Kwak, Moohyeon Kim, Sunghwan Kim, Taeyoon Kwon, Jiwan Chung, Youngjae Yu, Jinyoung Yeo
   • Presentation Type: Poster
   • Session: Generation 2, Session 11, 10:30-12:00
3. When “A Helpful Assistant” Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models
   • Link to Paper
   • Authors: Mingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran, Moontae Lee, David Jurgens
   • Presentation Type: Poster
   • Session: Interpretability and Analysis of Models for NLP 5, Session 11, 10:30-12:00
4. Gradient Localization Improves Lifelong Pretraining of Language Models
   • Link to Paper
   • Authors: Jared Fernandez, Yonatan Bisk, Emma Strubell
   • Presentation Type: Poster
   • Session: Machine Learning for NLP 3, Session 11, 10:30-12:00
5. BPO: Supercharging Online Preference Learning by Adhering to the Proximity of Behavior LLM
   
   • Link to Paper
   • Authors: Wenda Xu, Jiachen Li, William Yang Wang, Lei Li
   • Presentation Type: Poster
   • Session: Machine Learning for NLP 3, Session 11, 10:30-12:00
6. Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
   • Link to Paper
   • Authors: Aashiq Muhamed, Oscar Li, David Woodruff, Mona Diab, Virginia Smith
   • Presentation Type: Virtual Poster
   • Session: Special Theme: Efficiency in Model Algorithms, Training, and Inference, 13:00-14:00
7. MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
   • Link to Paper
   • Authors: Fengyu Cai, Xinran Zhao, Tong Chen, Sihao Chen, Hongming Zhang, Iryna Gurevych, Heinz Koeppl
   • Presentation Type: Poster
   • Session: Dialogue and Interactive Systems 3, Session 12, 14:00-15:30
8. AliGATr: Graph-based Layout Generation for Form Understanding
   • Link to Paper
   • Authors: Armineh Nourbakhsh, Zhao Jin, ,Siddharth Parekh, Sameena Shah, Carolyn Rose
   • Presentation Type: Poster
   • Session: Information Extraction 2, Session 12, 14:00-15:30
9. Extrinsic Evaluation of Cultural Competence in Large Language Models
   
   • Link to Paper
   • Authors: Shaily Bhatt and Fernando Diaz
   • Presentation Type: Poster
   • Session: Computational Social Science and Cultural Analytics 4, Session 12, 14:00-15:30

Not Presenting

1. Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
   
   • Link to Paper
   • Authors: Hyeonbin Hwang, Doyoung Kim, Seungone Kim, Seonghyeon Ye, Minjoon Seo
2. LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
   
   • Link to Paper
   • Authors: Yinquan Lu, Wenhao Zhu, Lei Li, Yu Qiao, Fei Yuan