大模型（LLM）精选42篇论文及开源代码汇总

在今年各大顶会的获奖论文中，大模型方向屡战头筹，这不难预料，自OpenAI发布ChatGPT至今，全球大模型热潮尚未停息，国内外已有相当多的大模型陆续出现，有些大模型的功能甚至不输ChatGPT。

在大模型“封神”的这段时间，相关的论文数量也十分吓人，我也拜读了不少优秀的作品，今天就精选了部分论文来和大家分享。

目前整理了42篇大模型论文，论文原文以及开源代码也都一并打包了，需要的资源包的同学文末领取。

精选论文（模型应用/评估、预训练、多模态、结构改进等）

1、Giraffe: Adventures in Expanding Context Lengths in LLMs

2、AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents

3、SeamlessM4T-Massively Multilingual & Multimodal Machine Translation

4、Instruction Tuning for Large Language Models: A Survey

5、SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

6、Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

7、Assessing Keyness using Permutation Tests

8、SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts

9、Multivariate Time Series Anomaly Detection: Fancy Algorithms and Flawed Evaluation Methodology

10、VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection

11、Open Gaze: An Open-Source Implementation Replicating Google's Eye Tracking Paper

12、Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering

13、Causal Parrots: Large Language Models May Talk Causality But Are Not Causal

14、A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions

15、Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

16、LLM2KB: Constructing Knowledge Bases using instruction tuned context aware Large Language Models

17、ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

18、COCO: Testing Code Generation Systems via Concretized Instructions

19、ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance

20、ZeroLeak: Using LLMs for Scalable and Cost Effective Side-Channel Patching

21、Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

22、The Poison of Alignment

23、Code Llama: Open Foundation Models for Code

24、Approximating Online Human Evaluation of Social Chatbots with Prompting

25、Integrating LLMs and Decision Transformers for Language Grounded Generative Quality-Diversity

26、A Control Flow based Static Analysis of GRAFCET using Abstract Interpretation

27、To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Acceleration

28、Bayesian low-rank adaptation for large language models

29、Domain-specific ChatBots for Science using Embeddings

30、ChatHaruhi: Reviving Anime Character in Reality via Large Language Model

31、ProAgent: Building Proactive Cooperative AI with Large Language Models

32、A Survey on Large Language Model based Autonomous Agents

33、Graph of Thoughts: Solving Elaborate Problems with Large Language Models

通用、垂直领域大模型论文+项目

1、Financial News Analytics Using Fine-Tuned Llama 2 GPT Model（金融）

2、BloombergGPT: A Large Language Model for Finance（金融）

3、FinBERT: A Large Language Model for Extracting Information from Financial Text*（金融）

4、PMC-LLaMA: Towards Building Open-source Language Models for Medicine（医疗）

5、Ngambay-French Neural Machine Translation (sba-Fr)（翻译）

6、LLaMA: Open and Efficient Foundation Language Models（Meta）

7、Alpaca: A Strong, Replicable Instruction-Following Model（Stanford）

8、GLM: General Language Model Pretraining with Autoregressive Blank Infilling（清华）

9、GPT-4 Technical Report（OpenAI）

关注下方《学姐带你玩AI》

回复“LLM精选”获取全部论文+开源代码合集

码字不易，欢迎大家点赞评论收藏！