EMNLP - arXivDaily 期刊&会议

2406.19759 2024-10-10 cs.CL

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment

Orgest Xhelili, Yihong Liu, Hinrich Schütze

Comments EMNLP 2024 Findings

2406.18695 2024-10-10 cs.LG cs.AI cs.CL

Learning to Correct for QA Reasoning with Black-box LLMs

Jaehyung Kim, Dongyoung Kim, Yiming Yang

Comments 22 pages; EMNLP 2024 (long, main)

2406.18365 2024-10-10 cs.CL

Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability

Xinyu Hu, Li Lin, Mingqi Gao, Xunjian Yin, Xiaojun Wan

Comments Accepted by EMNLP 2024

2406.18164 2024-10-10 cs.CL cs.LG

Nebula: A discourse aware Minecraft Builder

Akshay Chaturvedi, Kate Thompson, Nicholas Asher

Comments EMNLP 2024 Findings

2406.14643 2024-10-10 cs.CV cs.AI cs.CL

Holistic Evaluation for Interleaved Text-and-Image Generation

Minqian Liu, Zhiyang Xu, Zihao Lin, Trevor Ashby, Joy Rimchala, Jiaxin Zhang, Lifu Huang

Comments EMNLP 2024 Main Conference. 15 pages, 6 figures, 7 tables. Website: https://vt-nlp.github.io/InterleavedEval/. Dataset: https://huggingface.co/mqliu/InterleavedBench

2406.12277 2024-10-10 cs.CL

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models

Xin Zhao, Naoki Yoshinaga, Daisuke Oba

Comments 29 pages, 8 figures, 25 tables, Accepted by EMNLP 2024 (Findings)

2406.12018 2024-10-10 cs.CL

CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

Yu Bai, Xiyuan Zou, Heyan Huang, Sanxing Chen, Marc-Antoine Rondeau, Yang Gao, Jackie Chi Kit Cheung

Comments EMNLP 2024 Main Conference

2406.11911 2024-10-10 cs.AI cs.CL cs.LG

A Notion of Complexity for Theory of Mind via Discrete World Models

X. Angelo Huang, Emanuele La Malfa, Samuele Marro, Andrea Asperti, Anthony Cohn, Michael Wooldridge

Comments Accepted EMNLP 2024, Website https://flecart.github.io/complexity-tom-dwm

2405.10443 2024-10-10 cs.CL cs.LG

Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation

Matthew Raffel, Victor Agostinelli, Lizhong Chen

Comments Accepted at EMNLP 2024

2405.06001 2024-10-10 cs.LG cs.AI cs.CL

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

Ruihao Gong, Yang Yong, Shiqiao Gu, Yushi Huang, Chengtao Lv, Yunchen Zhang, Xianglong Liu, Dacheng Tao

Comments Accepted by EMNLP 2024 Industry Track

2404.16563 2024-10-10 cs.CL

Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark

Elizabeth Fons, Rachneet Kaur, Soham Palande, Zhen Zeng, Tucker Balch, Manuela Veloso, Svitlana Vyetrenko

Comments Accepted to EMNLP 2024

2404.13947 2024-10-10 cs.CV

Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering

Dongze Hao, Qunbo Wang, Longteng Guo, Jie Jiang, Jing Liu

Comments Accepted to EMNLP 2024 Main Conference

2404.12726 2024-10-10 cs.CL

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works

Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu, Jiangjie Chen, Deqing Yang

Comments EMNLP 2024 camera-ready

2404.11023 2024-10-10 cs.HC cs.CL cs.LG

Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions

Leena Mathur, Paul Pu Liang, Louis-Philippe Morency

Comments EMNLP 2024 Main Conference

2404.06809 2024-10-10 cs.CL

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation

Ruotong Pan, Boxi Cao, Hongyu Lin, Xianpei Han, Jia Zheng, Sirui Wang, Xunliang Cai, Le Sun

Comments Accepted to EMNLP 2024 Main Conference. Our code, benchmark, and models are available at https://github.com/panruotong/CAG

2404.02655 2024-10-10 cs.CL

Calibrating the Confidence of Large Language Models by Eliciting Fidelity

Mozhi Zhang, Mianqiu Huang, Rundong Shi, Linsen Guo, Chong Peng, Peng Yan, Yaqian Zhou, Xipeng Qiu

Comments EMNLP 2024

2403.14236 2024-10-10 cs.LG cs.AI cs.CL

A Unified Framework for Model Editing

Akshat Gupta, Dev Sajnani, Gopala Anumanchipalli

Comments EMNLP 2024 Findings

2403.07175 2024-10-10 cs.CL cs.AI

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli

Comments EMNLP 2024 (Main)

2403.01121 2024-10-10 cs.LG cs.AI cs.SI

OpenGraph: Towards Open Graph Foundation Models

Lianghao Xia, Ben Kao, Chao Huang

Comments Accepted by EMNLP'2024

2402.12801 2024-10-10 cs.CL

Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting

Marco Naguib, Xavier Tannier, Aurélie Névéol

Comments Accepted to EMNLP Findings, 2024

2402.11958 2024-10-10 cs.CL

Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs

Anqi Li, Yu Lu, Nirui Song, Shuai Zhang, Lizhi Ma, Zhenzhong Lan

Comments Accepted to EMNLP Findings 2024. 24 pages, 6 figures, 9 tables

2402.08874 2024-10-10 cs.CL

Recurrent Alignment with Hard Attention for Hierarchical Text Rating

Chenxi Lin, Jiayu Ren, Guoxiu He, Zhuoren Jiang, Haiyan Yu, Xiaomin Zhu

Comments Accepted by EMNLP 2024 Main Conference

2402.06925 2024-10-10 cs.CL

A Thorough Examination of Decoding Methods in the Era of LLMs

Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, Wai Lam

Comments EMNLP 2024 Main

2401.10440 2024-10-10 cs.CL

Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models

Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer

Comments EMNLP 2024

2401.00757 2024-10-10 cs.SE cs.AI cs.CL cs.LO

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models

Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael R. Lyu

Comments Accepted by EMNLP 2024

2311.10054 2024-10-10 cs.CL cs.AI cs.CY cs.HC cs.LG

When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models

Mingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran, Moontae Lee, David Jurgens

Comments Accepted by Findings of EMNLP 2024

2309.07590 2024-10-10 cs.CL

Revisiting Supertagging for Faster HPSG Pasing

Olga Zamaraeva, Carlos Gómez-Rodríguez

Comments 16 pages, 3 figures. To appear at EMNLP-2024

2305.19118 2024-10-10 cs.CL

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, Zhaopeng Tu

Comments EMNLP 2024 (main conference)

2410.05600 2024-10-10 cs.CL

Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning

Ming Shan Hee, Aditi Kumaresan, Roy Ka-Wei Lee

Comments Accepted at EMNLP'24 (Main)

2410.05559 2024-10-10 cs.CL

Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification

Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris

Comments Accepted to EMNLP Findings