语言大模型 / LLM

"It's not like Jarvis, but it's pretty close!" -- Examining ChatGPT's Usage among Undergraduate Students in Computer Science

Ishika Joshi, Ritvik Budhiraja, Harshal D Akolekar, Jagat Sesh Challa, Dhruv Kumar

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted in ACE 2024: https://aceconference2024.github.io/aceconference2024/ We thank Shamik Sinha, Palak Bhardwaj, Rayyan Hussain, Kashvi Panvanda, Sidhartha Garg, Shagun Yadav, Yash Chillar, and Sourav Goyal for their assistance in the development of questionnaires, as well as their involvement in conducting selected interviews

ChatGPT as a commenter to the news: can LLMs generate human-like opinions?

Rayden Tseng, Suzan Verberne, Peter van der Putten

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Comments Published as Tseng, R., Verberne, S., van der Putten, P. (2023). ChatGPT as a Commenter to the News: Can LLMs Generate Human-Like Opinions?. In: Ceolin, D., Caselli, T., Tulin, M. (eds) Disinformation in Open Online Media. MISDOOM 2023. Lecture Notes in Computer Science, vol 14397. Springer, Cham

Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment

Fengli Xu, Jun Zhang, Chen Gao, Jie Feng, Yong Li

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；foundation model(abstract)；分类 cs.AI

DelucionQA: Detecting Hallucinations in Domain-specific Question Answering

Mobashir Sadat, Zhengyu Zhou, Lukas Lange, Jun Araki, Arsalan Gundroo, Bingqing Wang, Rakesh R Menon, Md Rizwan Parvez, Zhe Feng

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted in EMNLP 2023 (Findings)

ChatGPT Exhibits Gender and Racial Biases in Acute Coronary Syndrome Management

Angela Zhang, Mert Yuksekgonul, Joshua Guild, James Zou, Joseph C. Wu

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 19 pages, 2 tables, 2 figures

Surpassing GPT-4 Medical Coding with a Two-Stage Approach

Zhichao Yang, Sanjit Singh Batra, Joel Stremmel, Eran Halperin

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2023, December 10th, 2023, New Orleans, United States, 19 pages

Adapt in Contexts: Retrieval-Augmented Domain Adaptation via In-Context Learning

Quanyu Long, Wenya Wang, Sinno Jialin Pan

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Comments EMNLP 2023

DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries

Jianyou Wang, Kaicheng Wang, Xiaoyue Wang, Prudhviraj Naidu, Leon Bergen, Ramamohan Paturi

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments To appear in NeurIPS 2023 Datasets and Benchmarks Track

PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain

Wei Zhu, Xiaoling Wang, Huanran Zheng, Mosha Chen, Buzhou Tang

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

GPT-4 as an interface between researchers and computational software: improving usability and reproducibility

Juan C. Verduzco, Ethan Holbrook, Alejandro Strachan

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 22 pages, 7 figures

QASiNa: Religious Domain Question Answering using Sirah Nabawiyah

Muhammad Razif Rizqullah, Ayu Purwarianti, Alham Fikri Aji

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 6 Pages. In Proceeding of 10th International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA 2023)

"With Great Power Comes Great Responsibility!": Student and Instructor Perspectives on the influence of LLMs on Undergraduate Engineering Education

Ishika Joshi, Ritvik Budhiraja, Pranav Deepak Tanna, Lovenya Jain, Mihika Deshpande, Arjun Srivastava, Srinivas Rallapalli, Harshal D Akolekar, Jagat Sesh Challa, Dhruv Kumar

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Under review

Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity

Joseph Gatto, Omar Sharif, Parker Seegmiller, Philip Bohlman, Sarah Masud Preum

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Comments Under review GEM@EMNLP-2023, 12 pages

Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs

Chao Feng, Xinyu Zhang, Zichu Fei

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

The potential of LLMs for coding with low-resource and domain-specific programming languages

Artur Tarassow

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

What can we learn from Data Leakage and Unlearning for Law?

Jaydeep Borkar

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 5 pages, 8 figures, accepted to the first GenLaw workshop at ICML'23, Hawai'i

Multimodal LLMs for health grounded in individual-specific data

Anastasiya Belyaeva, Justin Cosentino, Farhad Hormozdiari, Krish Eswaran, Shravya Shetty, Greg Corrado, Andrew Carroll, Cory Y. McLean, Nicholas A. Furlotte

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Can LLMs be Good Financial Advisors?: An Initial Study in Personal Decision Making for Optimized Outcomes

Kausik Lakkaraju, Sai Krishna Revanth Vuruma, Vishal Pallagani, Bharath Muppasani, Biplav Srivastava

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Generation of Radiology Findings in Chest X-Ray by Leveraging Collaborative Knowledge

Manuela Daniela Danu, George Marica, Sanjeev Kumar Karn, Bogdan Georgescu, Awais Mansoor, Florin Ghesu, Lucian Mihai Itu, Constantin Suciu, Sasa Grbic, Oladimeji Farri, Dorin Comaniciu

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Information Technology and Quantitative Management (ITQM 2023)

Journal ref Information Technology and Quantitative Management (ITQM 2023

ChatGPT as your Personal Data Scientist

Md Mahadi Hassan, Alex Knipper, Shubhra Kanti Karmaker Santu

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

From Words to Code: Harnessing Data for Program Synthesis from Natural Language

Anirudh Khatry, Joyce Cahoon, Jordan Henkel, Shaleen Deep, Venkatesh Emani, Avrilia Floratou, Sumit Gulwani, Vu Le, Mohammad Raza, Sherry Shi, Mukul Singh, Ashish Tiwari

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 14 pages

Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations

Jungo Kasai, Yuhei Kasai, Keisuke Sakaguchi, Yutaro Yamada, Dragomir Radev

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Added results from the March 2023 exam

Yes but.. Can ChatGPT Identify Entities in Historical Documents?

Carlos-Emiliano González-Gallardo, Emanuela Boros, Nancy Girdhar, Ahmed Hamdi, Jose G. Moreno, Antoine Doucet

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Comments 5 pages, accepted to JCDL2023

Task formulation for Extracting Social Determinants of Health from Clinical Narratives

Manabu Torii, Ian M. Finn, Son Doan, Paul Wang, Elly W. Yang, Daniel S. Zisook

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

AI Cosplaying as Astrophysicists: A Controlled Synthetic-Agent Study of AI-Assisted Astrophysical Research Workflows

AI 伪装成天体物理学家：一个受控的合成智能体研究，探讨AI辅助天体物理研究流程

Chun Huang

专题命中 领域大模型 ：language model(abstract,comments)；LLM(abstract)；large language model(abstract)

AI总结 本文通过模拟144名合成研究者完成2592项日常天体物理研究任务，评估AI在不同任务类型和使用风格下的效果，发现AI辅助在特定任务和使用策略下能提升效率，但对推导密集型任务存在风险。

Comments 16 pages, 8 figures. Began as an April Fools' idea, regrettably became a real methods paper, No language models were physically harmed. GitHub repository of this work: https://github.com/ChunHuangPhy/agent_astro

D-Rax: Domain-specific Radiologic assistant leveraging multi-modal data and eXpert model predictions

Hareem Nisar, Syed Muhammad Anwar, Zhifan Jiang, Abhijeet Parida, Ramon Sanchez-Jacob, Vishwesh Nath, Holger R. Roth, Marius George Linguraru

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG；foundation model(comments)

Comments accepted to the MICCAI 2024 Second International Workshop on Foundation Models for General Medical AI

Monkey King Bang: A Unified Scientific Multimodal Foundation Model

孙悟空爆炸：一个统一的科学多模态基础模型

Hesen Chen, Xinyu Su, Xiaomeng Yang, Yuetan Lin, Zixiong Yang, Junyi An, Fenglei Cao, Yifeng Jiao, Yunqi Zhang, Yuan Cheng, Zhiyu Tan, Hao Li, Libo Wu, Yuan Qi

机构 * Shanghai Academy of AI for Science（上海人工智能研究院） 纠错

专题命中 领域大模型 ：foundation model(title)；分类 cs.AI、cs.LG

AI总结 研究针对科学多领域推理需求，引入统一科学多模态模型MKB，围绕共享Transformer主干及定制组件构建，涵盖多科学分支。通过两阶段训练，在多方面实验表现出色，证明该范式可行，为跨领域科学多模态探索提供基础。

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language

一致但校准错误：评估大语言模型在自然语言风险沟通中的局限性

Diego Cerda-Mardini, Sarath Chandar, Sreenath Madathil

机构 * Faculty of Dental Medicine and Oral Health Sciences, McGill University（麦吉尔大学牙医学与口腔健康科学学院） ； Chandar Research Lab, Polytechnique Montréal（蒙特利尔理工大学钱达尔研究实验室） ； Mila – Québec Artificial Intelligence Institute（魁北克人工智能研究所米拉） ； Département de Génie Informatique et Génie Logiciel (GIGL), Polytechnique Montréal（蒙特利尔理工大学计算机科学与软件工程系） 纠错

专题命中 领域大模型 ：LLM(title)；分类 cs.CL、cs.AI

AI总结 研究大语言模型在自然语言中传达概率信息的可靠性，在两阶段预测管道中评估九个模型，发现其一致但校准错误，提供预计算统计量未解决问题，表明当前模型非可靠零样本风险沟通工具。

Internal Representation, Not Clinical Knowledge: Where Apparent LLM Triage Failures Originate

内部表示，而非临床知识：明显的大语言模型分诊失败源于何处

David Fraile Navarro, Berardino Como, Jialei Sheng, Soundariya Ananthan, Shlomo Berkovsky

机构 * Macquarie University（麦考瑞大学） ； Politecnico di Bari（巴里理工大学） ； NSW Health（新南威尔士州卫生部） ； Independent Researcher（独立研究者） 纠错

专题命中 领域大模型 ：LLM(title)；分类 cs.CL、cs.AI

AI总结 本研究通过稀疏自编码器特征分析，发现大语言模型在分诊任务中表现不佳源于输出格式限制，而非临床知识表示缺陷。

Comments 9 pages main text, 27 pages total including appendices; 7 figures, 25 tables

Unlocking LLM Creativity in Science through Analogical Reasoning

通过类比推理解锁大语言模型在科学中的创造力

Andrew Shen, Shaul Druckmann, James Zou

机构 * Stanford University（斯坦福大学） 纠错

专题命中 领域大模型 ：LLM(title)；分类 cs.CL、cs.AI

AI总结 本文通过类比推理方法提升大语言模型在开放性问题解决中的多样性与创新性，实验表明该方法显著提高了生成解决方案的质量和多样性。