Computation and Language

Authors and titles for cs.CL in Nov 2023

[1]  arXiv:2311.00116 [pdf, other]

Title: BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text

Authors: Aarohi Srivastava, David Chiang

Comments: Accepted for publication in Findings of the ACL: EMNLP 2023

Subjects: Computation and Language (cs.CL)

[2]  arXiv:2311.00117 [pdf, other]

Title: BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

Authors: Pranav Gade, Simon Lermen, Charlie Rogers-Smith, Jeffrey Ladish

Subjects: Computation and Language (cs.CL)

[3]  arXiv:2311.00128 [pdf, other]

Title: On the effect of curriculum learning with developmental data for grammar acquisition

Authors: Mattia Opper, J. Morrison, N. Siddharth

Comments: CoNLL-CMCL Shared Task BabyLM Challenge 2023

Subjects: Computation and Language (cs.CL)

[4]  arXiv:2311.00159 [pdf, other]

Title: Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networks

Authors: Xinting Huang, Jiajing Wan, Ioannis Kritikos, Nora Hollenstein

Subjects: Computation and Language (cs.CL)

[5]  arXiv:2311.00161 [pdf, other]

Title: Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language

Authors: Jimin Mun, Emily Allaway, Akhila Yerukola, Laura Vianna, Sarah-Jane Leslie, Maarten Sap

Comments: EMNLP 2023 Findings, 19 pages

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[6]  arXiv:2311.00172 [pdf, other]

Title: Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield

Authors: Jinhwa Kim, Ali Derakhshan, Ian G. Harris

Comments: 11 pages, 2 figures

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[7]  arXiv:2311.00176 [pdf, other]

Title: ChipNeMo: Domain-Adapted LLMs for Chip Design

Authors: Mingjie Liu, Teodor-Dumitru Ene, Robert Kirby, Chris Cheng, Nathaniel Pinckney, Rongjian Liang, Jonah Alben, Himyanshu Anand, Sanmitra Banerjee, Ismet Bayraktaroglu, Bonita Bhaskaran, Bryan Catanzaro, Arjun Chaudhuri, Sharon Clay, Bill Dally, Laura Dang, Parikshit Deshpande, Siddhanth Dhodhi, Sameer Halepete, Eric Hill, Jiashang Hu, Sumit Jain, Ankit Jindal, Brucek Khailany, George Kokai, Kishor Kunal, Xiaowei Li, Charley Lind, Hao Liu, Stuart Oberman, Sujeet Omar, Ghasem Pasandi, Sreedhar Pratty, Jonathan Raiman, Ambar Sarkar, Zhengjiang Shao, Hanfei Sun, Pratik P Suthar, Varun Tej, Walker Turner, Kaizhe Xu, Haoxing Ren

Comments: Updated results for ChipNeMo-70B model

Subjects: Computation and Language (cs.CL)

[8]  arXiv:2311.00189 [pdf, other]

Title: XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision

Authors: Daniel Hajialigol, Hanwen Liu, Xuan Wang

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[9]  arXiv:2311.00204 [pdf, other]

Title: Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering

Authors: Zhen Guo, Yining Hua

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[10]  arXiv:2311.00223 [pdf, other]

Title: Is GPT Powerful Enough to Analyze the Emotions of Memes?

Authors: Jingjing Wang, Joshua Luo, Grace Yang, Allen Hong, Feng Luo

Subjects: Computation and Language (cs.CL); Multimedia (cs.MM)

[11]  arXiv:2311.00233 [pdf, other]

Title: Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions

Authors: Taehyeon Kim, Joonkee Kim, Gihun Lee, Se-Young Yun

Comments: ICLR 2024 (Spotlight)

Subjects: Computation and Language (cs.CL)

[12]  arXiv:2311.00237 [pdf, other]

Title: The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis

Authors: Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He

Subjects: Computation and Language (cs.CL)

[13]  arXiv:2311.00258 [pdf, other]

Title: Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis

Authors: Hongyi Zheng, Abulhair Saparov

Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG)

[14]  arXiv:2311.00262 [pdf, other]

Title: Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents

Authors: Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Comments: Accepted by ICLR 2024

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[15]  arXiv:2311.00268 [pdf, other]

Title: Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?

Authors: Luke Gessler, Nathan Schneider

Comments: Accepted at CoNLL 2023

Subjects: Computation and Language (cs.CL)

[16]  arXiv:2311.00273 [pdf, other]

Title: SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations

Authors: Yirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng, Zhenyu Wang, Qi Liu, Xiangmin Xu

Comments: Appectped to Findings of EMNLP2023

Subjects: Computation and Language (cs.CL)

[17]  arXiv:2311.00286 [pdf, other]

Title: JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models

Authors: Mi Zhang, Xudong Pan, Min Yang

Comments: A preprint work. Benchmark link: this https URL Website link: this https URL

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)

[18]  arXiv:2311.00287 [pdf, other]

Title: Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models

Authors: Ran Xu, Hejie Cui, Yue Yu, Xuan Kan, Wenqi Shi, Yuchen Zhuang, Wei Jin, Joyce Ho, Carl Yang

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)

[19]  arXiv:2311.00288 [pdf, other]

Title: Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks

Authors: Po-Nien Kung, Fan Yin, Di Wu, Kai-Wei Chang, Nanyun Peng

Comments: EMNLP 2023 Main

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[20]  arXiv:2311.00292 [pdf, other]

Title: IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models

Authors: Xiaoyue Wang, Xin Liu, Lijie Wang, Yaoxiang Wang, Jinsong Su, Hua Wu

Comments: EMNLP2023 main conference

Subjects: Computation and Language (cs.CL)

[21]  arXiv:2311.00296 [pdf, ps, other]

Title: Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Network

Authors: Hongrui Gao, Yawen Li, Meiyu Liang, Zeli Guan, Zhe Xue

Subjects: Computation and Language (cs.CL)

[22]  arXiv:2311.00300 [pdf, ps, other]

Title: Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion

Authors: Runze Fang, Yawen Li, Yingxia Shao, Zeli Guan, Zhe Xue

Subjects: Computation and Language (cs.CL)

[23]  arXiv:2311.00306 [pdf, other]

Title: Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation

Authors: Xiangjue Dong, Yibo Wang, Philip S. Yu, James Caverlee

Comments: Accepted in Socially Responsible Language Modelling Research (SoLaR) 2023 at NeurIPS 2023; the first two authors contribute equally

Subjects: Computation and Language (cs.CL)

[24]  arXiv:2311.00310 [pdf, other]

Title: Unsupervised Lexical Simplification with Context Augmentation

Authors: Takashi Wada, Timothy Baldwin, Jey Han Lau

Comments: 12 pages; accepted for the Findings of EMNLP 2023

Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

[25]  arXiv:2311.00317 [pdf, other]

Title: Data Augmentation for Code Translation with Comparable Corpora and Multiple References

Authors: Yiqing Xie, Atharva Naik, Daniel Fried, Carolyn Rose

Comments: EMNLP 2023 Findings

Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Software Engineering (cs.SE)