EMNLP - arXivDaily 期刊&会议

2402.13950 2024-10-08 cs.CL

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Debjit Paul, Robert West, Antoine Bosselut, Boi Faltings

Comments Accepted at EMNLP Findings

2402.10353 2024-10-08 cs.CL cs.LG

Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models

Kang He, Yinghan Long, Kaushik Roy

Comments EMNLP 2024 Findings

2402.03469 2024-10-08 cs.LG cs.AI cs.CL

Rethinking the Role of Proxy Rewards in Language Model Alignment

Sungdong Kim, Minjoon Seo

Comments Accepted to EMNLP 2024 main conference

2402.02987 2024-10-08 cs.CR cs.AI cs.CL cs.LG

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

Junjie Chu, Zeyang Sha, Michael Backes, Yang Zhang

Comments Accepted in EMNLP 2024. 14 pages, 10 figures

2401.05930 2024-10-08 cs.CL cs.AI

SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully

Jushi Kai, Tianhang Zhang, Hai Hu, Zhouhan Lin

Comments EMNLP 2024 Findings

2312.17044 2024-10-08 cs.CL

Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding

Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, Ting Liu

Comments Accepted to EMNLP 2024 Findings

2312.05621 2024-10-08 cs.CL

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching

Zhenting Qi, Xiaoyu Tan, Shaojie Shi, Chao Qu, Yinghui Xu, Yuan Qi

Comments Accepted by EMNLP 2023 (Industry Track), Oral Presentation

2311.13538 2024-10-08 cs.AI cs.LG

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations

Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang

Comments Findings of EMNLP 2024

2311.07064 2024-10-08 cs.CL

Prompts have evil twins

Rimon Melamed, Lucas H. McCabe, Tanay Wakhare, Yejin Kim, H. Howie Huang, Enric Boix-Adsera

Comments EMNLP 2024 Main, camera-ready

2410.04282 2024-10-08 cs.CL

Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia

Farhan Samir, Chan Young Park, Anjalie Field, Vered Shwartz, Yulia Tsvetkov

Comments 15 pages, 3 figures. To appear at EMNLP'24

2410.04269 2024-10-08 cs.CL

RoQLlama: A Lightweight Romanian Adapted Language Model

George-Andrei Dima, Andrei-Marius Avram, Cristian-George Crăciun, Dumitru-Clementin Cercel

Comments Accepted at EMNLP Findings 2024 (short papers)

2410.04164 2024-10-08 cs.CL

Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling

Huije Lee, Hoyun Song, Jisu Shin, Sukmin Cho, SeungYoon Han, Jong C. Park

Comments Findings of EMNLP 2024

2410.04148 2024-10-08 cs.CL cs.AI

Reasoning with Natural Language Explanations

Marco Valentino, André Freitas

Comments Tutorial to be presented at EMNLP 2024. Website: https://sites.google.com/view/reasoning-with-explanations

2410.04103 2024-10-08 cs.CL

A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models

Zhihao Wang, Shiyu Liu, Jianheng Huang, Zheng Wang, Yixuan Liao, Xiaoxin Chen, Junfeng Yao, Jinsong Su

Comments EMNLP 2024 (main,long paper)

2410.04087 2024-10-08 cs.CL cs.AI

GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization

Yangfan Ye, Xiachong Feng, Xiaocheng Feng, Weitao Ma, Libo Qin, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Comments EMNLP 2024 main conference, long paper

2410.04075 2024-10-08 cs.CL

PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation

Libo Zhao, Jing Li, Ziqian Zeng

Comments Accepted to EMNLP 2024 main conference

2410.04074 2024-10-08 cs.CL cs.AI cs.LG

On Eliciting Syntax from Language Models via Hashing

Yiran Wang, Masao Utiyama

Comments EMNLP-2024

2410.04068 2024-10-08 cs.CL cs.AI

ECon: On the Detection and Resolution of Evidence Conflicts

Cheng Jiayang, Chunkit Chan, Qianqian Zhuang, Lin Qiu, Tianhang Zhang, Tengxiao Liu, Yangqiu Song, Yue Zhang, Pengfei Liu, Zheng Zhang

Comments Accepted by EMNLP 2024 main conference

2410.04027 2024-10-08 cs.CL

A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models

Houquan Zhou, Zhenghua Li, Bo Zhang, Chen Li, Shaopeng Lai, Ji Zhang, Fei Huang, Min Zhang

Comments Accepted at Main Conference of EMNLP 2024

2410.03996 2024-10-08 cs.CL

On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models

Abhilasha Sancheti, Haozhe An, Rachel Rudinger

Comments Accepted to EMNLP 2024

2410.03925 2024-10-08 cs.CL cs.IR

C3PA: An Open Dataset of Expert-Annotated and Regulation-Aware Privacy Policies to Enable Scalable Regulatory Compliance Audits

Maaz Bin Musa, Steven M. Winston, Garrison Allen, Jacob Schiller, Kevin Moore, Sean Quick, Johnathan Melvin, Padmini Srinivasan, Mihailis E. Diamantis, Rishab Nithyanand

Comments 9 pages, EMNLP 2024

2410.03907 2024-10-08 cs.CL

ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities

Ying Su, Zhan Ling, Haochen Shi, Jiayang Cheng, Yauwai Yim, Yangqiu Song

Comments 13 pages, 9 figures, 8 tables, accepted to EMNLP 2024 main conference

2410.03884 2024-10-08 cs.CL cs.AI cs.CY cs.HC

KidLM: Advancing Language Models for Children -- Early Insights and Future Directions

Mir Tafseer Nayeem, Davood Rafiei

Comments Accepted to EMNLP 2024 (long, main)

2410.03870 2024-10-08 cs.CL

From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues

Yu Li, Devamanyu Hazarika, Di Jin, Julia Hirschberg, Yang Liu

Comments Findings of EMNLP 2024, 19 pages

2410.03829 2024-10-08 cs.CL

Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation

Chu Fei Luo, Radin Shayanfar, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu

Comments 8.5 pages of main body, 20 pages total; Accepted to Findings of EMNLP 2024

2410.03750 2024-10-08 cs.LG cs.AI cs.CL

SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models

Juan Pablo Muñoz, Jinjie Yuan, Nilesh Jain

Comments To be published in EMNLP-24 Findings

2410.03743 2024-10-08 cs.CL cs.AI cs.LG

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging

Yiming Ju, Ziyi Ni, Xingrun Xing, Zhixiong Zeng, hanyu Zhao, Siqi Fan, Zheng Zhang

Comments EMNLP 2024

2410.00822 2024-10-08 cs.SD cs.CL eess.AS

VHASR: A Multimodal Speech Recognition System With Vision Hotwords

Jiliang Hu, Zuchao Li, Ping Wang, Haojun Ai, Lefei Zhang, Hai Zhao

Comments 14 pages, 6 figures, accepted by EMNLP 2024

2409.20365 2024-10-08 cs.CV

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs

Ruotong Liao, Max Erler, Huiyu Wang, Guangyao Zhai, Gengyuan Zhang, Yunpu Ma, Volker Tresp

Comments EMNLP 2024 Findings; 22 pages; Code: https://github.com/mayhugotong/VideoINSTA

2409.17745 2024-10-08 cs.IR cs.CL cs.LG

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly, Debasis Samanta, Pabitra Mitra

Comments Accepted to EMNLP 2024