Papers › Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and...
Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations
David Nadeau, Mike Kroutikov, Karen McNeil, Simon Baribeau
This paper introduces fourteen novel datasets for the evaluation of Large Language Models' safety in the context of enterprise tasks. A method was devised to evaluate a model's safety, as determined by its ability to follow instructions and output factual, unbiased, grounded, and appropriate content. In this research, we used OpenAI GPT as point of comparison since it excels at all levels of safety. On the open-source side, for smaller models, Meta Llama2 performs well at factuality and toxicity but has the highest propensity for hallucination. Mistral hallucinates the least but cannot handle toxicity well. It performs well in a dataset mixing several tasks and safety vectors in a narrow vertical domain. Gemma, the newly introduced open-source model based on Google Gemini, is generally balanced but trailing behind. When engaging in back-and-forth conversation (multi-turn prompts), we find that the safety of open-source models degrades significantly. Aside from OpenAI's GPT, Mistral is the only model that still performed well in multi-turn tests.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.09785")
Code
Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 7 ran with no contract checked.
By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from innodatalabs/innodata-llm-safety. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
d588d40022bd695a · report
f6149b7760914f4b · report
e4c386a84cba8e32 · report
474aa0523777da52 · report
3fdbced8ead7865b · report
68ce2da084a8ce5b · report
fb1d765e46465110 · report
47b1553cc5bb77ad · report
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Bias Detection | rt-inod-bias | GPT-4 | Best-of | 0.5 | #1 of 5 | Archive leaderboard | report |
| Bias Detection | rt-inod-bias | Gemma | Best-of | 0.41 | #2 of 5 | Archive leaderboard | report |
| Bias Detection | rt-inod-bias | Baseline | Best-of | 0.41 | #3 of 5 | Archive leaderboard | report |
| Bias Detection | rt-inod-bias | Mistral | Best-of | 0.36 | #4 of 5 | Archive leaderboard | report |
| Bias Detection | rt-inod-bias | Llama2 | Best-of | 0.34 | #5 of 5 | Archive leaderboard | report |
| Dialogue Safety Prediction | rt-inod-jailbreaking | Baseline | Best-of | 0.92 | #1 of 5 | Archive leaderboard | report |
| Dialogue Safety Prediction | rt-inod-jailbreaking | GPT-4 | Best-of | 0.91 | #2 of 5 | Archive leaderboard | report |
| Dialogue Safety Prediction | rt-inod-jailbreaking | Gemma | Best-of | 0.91 | #3 of 5 | Archive leaderboard | report |
| Dialogue Safety Prediction | rt-inod-jailbreaking | Mistral | Best-of | 0.87 | #4 of 5 | Archive leaderboard | report |
| Dialogue Safety Prediction | rt-inod-jailbreaking | Llama2 | Best-of | 0.86 | #5 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections