m0o0scar

[github] ol-th/pdf-img-convert.js

Source

JavaScript / 297 lines of code. Simple node package to convert a PDF into images.

URL: https://github.com/ol-th/pdf-img-convert.js

Conversation

m0o0scar

[arxiv] Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Source

Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution. Knowledge utilization delves into the mechanism of memorization, comprehension and application, and creation. Knowledge evolution focuses on the dynamic progression of knowledge within individual and group LLMs. Moreover, we discuss what knowledge LLMs have learned, the reasons for the fragility of parametric knowledge, and the potential dark knowledge (hypothesis) that will be challenging to address. We hope this work can help understand knowledge in LLMs and provide insights for future research.

URL: https://huggingface.co

m0o0scar

[arxiv] Internal Consistency and Self-Feedback in Large Language Models: A Survey

Source

Xun Liang, Shichao Song, Zifan Zheng, Hanyu Wang, Qingchen Yu, Xunkai Li, Rong-Hua Li, Feiyu Xiong, Zhiyu Li

Large language models (LLMs) are expected to respond accurately but often exhibit deficient reasoning or generate hallucinatory content. To address these, studies prefixed with ``Self-'' such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a commonality: involving LLMs evaluating and updating itself to mitigate the issues. Nonetheless, these efforts lack a unified perspective on summarization, as existing surveys predominantly focus on categorization without examining the motivations behind these works. In this paper, we summarize a theoretical framework, termed Internal Consistency, which offers unified explanations for phenomena such as the lack of reasoning and the presence of hallucinations. Internal Consistency assesses the coherence among LLMs' latent layer, deco

m0o0scar

[arxiv] Internal Consistency and Self-Feedback in Large Language Models: A Survey

Source

Xun Liang, Shichao Song, Zifan Zheng, Hanyu Wang, Qingchen Yu, Xunkai Li, Rong-Hua Li, Feiyu Xiong, Zhiyu Li

Large language models (LLMs) are expected to respond accurately but often exhibit deficient reasoning or generate hallucinatory content. To address these, studies prefixed with ``Self-'' such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a commonality: involving LLMs evaluating and updating itself to mitigate the issues. Nonetheless, these efforts lack a unified perspective on summarization, as existing surveys predominantly focus on categorization without examining the motivations behind these works. In this paper, we summarize a theoretical framework, termed Internal Consistency, which offers unified explanations for phenomena such as the lack of reasoning and the presence of hallucinations. Internal Consistency assesses the coherence among LLMs' latent layer, deco

m0o0scar

[github] stanford-oval/storm

Source

Python / 5.5K lines of code. An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

URL: https://github.com/stanford-oval/storm

Conversation

m0o0scar

[arxiv] OpenDevin: An Open Platform for AI Software Developers as Generalist Agents

Source

Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, Graham Neubig

Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways. At the same time, thanks to improvements in large language models (LLMs), there has also been a rapid development in AI agents that interact with and affect change in their surrounding environments. In this paper, we introduce OpenDevin, a platform for the development of powerful and flexible AI agents that interact with the world in similar ways to those of a human developer: by writing code, interacting with a command line, and browsi

m0o0scar

[arxiv] OpenDevin: An Open Platform for AI Software Developers as Generalist Agents

Source

Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, Graham Neubig

Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways. At the same time, thanks to improvements in large language models (LLMs), there has also been a rapid development in AI agents that interact with and affect change in their surrounding environments. In this paper, we introduce OpenDevin, a platform for the development of powerful and flexible AI agents that interact with the world in similar ways to those of a human developer: by writing code, interacting with a command line, and browsi

m0o0scar

[
    {"name": "Afghanistan", "code": "AF"},
    {"name": "Åland Islands", "code": "AX"},
    {"name": "Albania", "code": "AL"},
    {"name": "Algeria", "code": "DZ"},
    {"name": "American Samoa", "code": "AS"},
    {"name": "AndorrA", "code": "AD"},
    {"name": "Angola", "code": "AO"},
    {"name": "Anguilla", "code": "AI"},
    {"name": "Antarctica", "code": "AQ"},

m0o0scar

<!DOCTYPE html>
<html>
  <head>
    <meta charset="UTF-8">
    <!-- https://developer.mozilla.org/en-US/docs/Web/HTTP/CSP -->
    <meta http-equiv="Content-Security-Policy" content="default-src 'self'; script-src 'self'">
    <meta http-equiv="X-Content-Security-Policy" content="default-src 'self'; script-src 'self'">
    <title>Hello World!</title>
  </head>
  <body>

m0o0scar

<!DOCTYPE html>
<html>
  <head>
    <meta charset="UTF-8">
    <title>Hello World!</title>
  </head>
  <body>
    <h1>iPhone 12 HDR Video Test</h1>

    <p id="userAgent"></p>