Skip to content

Commit

Permalink
domain migration, updated news and publications
Browse files Browse the repository at this point in the history
  • Loading branch information
deepakn97 committed Nov 27, 2023
1 parent 146c243 commit d940914
Show file tree
Hide file tree
Showing 2 changed files with 17 additions and 4 deletions.
13 changes: 13 additions & 0 deletions _bibliography/papers.bib
Original file line number Diff line number Diff line change
Expand Up @@ -116,4 +116,17 @@ @misc{nathani2023maf
bibtex_show = true,
abbr = "EMNLP",
pdf = "https://arxiv.org/pdf/2310.12426.pdf",
}

@misc{pan2023automatically,
title={Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies},
author={Liangming Pan and Michael Saxon and Wenda Xu and Deepak Nathani and Xinyi Wang and William Yang Wang},
abstract={Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback. This paper presents a comprehensive review of this emerging class of techniques. We analyze and taxonomize a wide array of recent work utilizing these strategies, including training-time, generation-time, and post-hoc correction. We also summarize the major applications of this strategy and conclude by discussing future directions and challenges},
year={2023},
eprint={2308.03188},
archivePrefix={arXiv},
primaryClass={cs.CL},
bibtex_show=true,
abbr="Arxiv",
pdf="https://arxiv.org/pdf/2308.03188.pdf"
}
8 changes: 4 additions & 4 deletions _config.yml
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ footer_text: >
lang: en # the language of your site (for example: en, fr, cn, ru, etc.)
icon: 💻 # the emoji used as the favicon (alternatively, provide image name in /assets/img/)

url: https://deepakn97.github.io # the base hostname & protocol for your site
url: https://www.dnathani.net # the base hostname & protocol for your site
baseurl: # the subpath of your site, e.g. /blog/
last_updated: true # set to true if you want to display last updated in the footer
impressum_path: # set to path to include impressum link in the footer, use the same path as permalink in a page, helps to conform with EU GDPR
Expand Down Expand Up @@ -146,8 +146,8 @@ collections:
output: true
permalink: /projects/:path/

news_scrollable: false # adds a vertical scroll bar if there are more than 3 news items
news_limit: 3 # leave blank to include all the news in the `_news` folder
news_scrollable: true # adds a vertical scroll bar if there are more than 3 news items
news_limit: # leave blank to include all the news in the `_news` folder

# -----------------------------------------------------------------------------
# Jekyll settings
Expand Down Expand Up @@ -259,7 +259,7 @@ scholar:
filtered_bibtex_keywords: [abbr, abstract, arxiv, bibtex_show, html, pdf, selected, supp, blog, code, poster, slides, website, preview, altmetric]

# Maximum number of authors to be shown for each publication (more authors are visible on click)
max_author_limit: 3 # leave blank to always show all authors
max_author_limit: 5 # leave blank to always show all authors
more_authors_animation_delay: 10 # more authors are revealed on click using animation; smaller delay means faster animation


Expand Down

0 comments on commit d940914

Please sign in to comment.