HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
Libr-AI
OpenFactVerification
Python2024–2024
Libr-AI / OpenFactVerification

OpenFactVerification

Loki: Open-source solution designed to automate the process of verifying factuality

3Distinct people
7Mentions
0Explicit recommenders
1.2KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Loki: Open-source solution designed to automate the process of verifying factuality

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day7 dated mentions

Observed mentions: 2024-04-06 10:59:01 UTC to 2024-04-17 17:38:28 UTC.

0123452024-04-06 00:00:00 UTC to 2024-04-07 00:00:00 UTC (exclusive): 5 mentions; 1 submissions, 4 commentsApr 62024-04-07 00:00:00 UTC to 2024-04-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-08 00:00:00 UTC to 2024-04-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-09 00:00:00 UTC to 2024-04-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-10 00:00:00 UTC to 2024-04-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-11 00:00:00 UTC to 2024-04-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsApr 112024-04-12 00:00:00 UTC to 2024-04-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-13 00:00:00 UTC to 2024-04-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-14 00:00:00 UTC to 2024-04-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-15 00:00:00 UTC to 2024-04-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-16 00:00:00 UTC to 2024-04-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-17 00:00:00 UTC to 2024-04-18 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 commentsApr 17

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Apr 62024-04-06 00:00:00 UTC2024-04-07 00:00:00 UTC514
Apr 72024-04-07 00:00:00 UTC2024-04-08 00:00:00 UTC000
Apr 82024-04-08 00:00:00 UTC2024-04-09 00:00:00 UTC000
Apr 92024-04-09 00:00:00 UTC2024-04-10 00:00:00 UTC000
Apr 102024-04-10 00:00:00 UTC2024-04-11 00:00:00 UTC000
Apr 112024-04-11 00:00:00 UTC2024-04-12 00:00:00 UTC000
Apr 122024-04-12 00:00:00 UTC2024-04-13 00:00:00 UTC000
Apr 132024-04-13 00:00:00 UTC2024-04-14 00:00:00 UTC000
Apr 142024-04-14 00:00:00 UTC2024-04-15 00:00:00 UTC000
Apr 152024-04-15 00:00:00 UTC2024-04-16 00:00:00 UTC000
Apr 162024-04-16 00:00:00 UTC2024-04-17 00:00:00 UTC000
Apr 172024-04-17 00:00:00 UTC2024-04-18 00:00:00 UTC211

What Hacker News says

7 sources
Hello vinni2, thank you for mentioning the paper. However, I noticed that it hasn't gone through peer review yet. Also, the paper suggests that fine-tuning may work better than in-context learning, but that's not a problem. You can fine-tune any LLMs like GPT-3.5 for this purpose and use them with this framework. Once you have fine-tuned GPT, for example, with specific data, you'll only need to modify the model name (https://github.com/Libr-AI/OpenFactVerification/blob/8fd1da9...). I believe this approach can lead to better results than what the paper suggests.
In Loki: An open-source tool for fact verification
Hi there, I agree that fact-checking is not something that current generative AI models can directly solve. Therefore, we decompose this complex into five simpler steps, which current techniques can better solve. Please refer to https://github.com/Libr-AI/OpenFactVerification?tab=readme-o... for more details. However, errors can always occur. We try to help users in an interpretable and transparent way by showing all retrieved evidence and the rationale behind each assessment. We hope this could at least help people when dealing with such problems.
In Loki: An open-source tool for fact verification

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.