Viewing profile — kostaj

Yes, you can check out Lenz without the API here: https://lenz.io/verify Also examples of claims other people have verified with Lenz: https://lenz.io/library

[flagged]

[flagged]

[flagged]

Some models struggle combining JSON schema and web search capabilities.

Good point. Will publish in the next version also the results with a prompt that allows the models to "think out loud" before providing the final verdict.

Awesome. We do plan to human-label the 1,000 claims and then compare Lenz' performance vs the 5 models. We've done some limited internal research with 150 claims, but more are need…

Agree that some of the claims are forward-looking. The messiness of the real-world and real-user fact checks. No ground-truth verdicts are provided or used in the study though. It …

Good idea about publishing intra-model variance data! Will include in the next version. Even if we put aside the two middle buckets (Mostly True and Misleading), that are somewhat …

Good point. Processing the substance of the answer might be too labor-consuming (1,000 claims x 5 models), but "thinking out loud" might improve the quality of the answers indeed. …

This is in line with my observations and tests as well. Also supported by the distribution of the verdicts across the 4-buckets -- Gemini uses the middle buckets (Mostly True and M…

Indeed. For algorithms and coding, my personal routine nowadays is to review every detailed plan with Opus 4.7 and GPT-5.5. They tend to find very different type of gaps.

Agree that True and Mostly True might be very close and could be a calibration difference. Misleading and False, as well. A better headline number might be the 34% claims with subs…

Agree. Human experts also struggle agreeing on this type of claims. The inter-annotator agreement on the verdicts on the AVeriTeC corpus across 50 organizations is κ=0.619 - substa…

Agree with @pjdesno, that the 34% substantive or polar disagreement might be a better headline number. Or even the 21% polar disagreement (at least one model True, and at least one…

That's a valid point. During the preliminary research, we did try also more explicit prompts (with explanation for each of the 4 buckets), as well as a five-bucket rubric (with Abs…

Quick note on the second effect - how LLMs reduce that to a four-category judgment: On 21% of the claims at least two models provide polar-opposite verdicts (at least one model Fal…

Agree about comparing models with and without search capabilities. Even the two models with search capabilities (Sonar Pro and Gemini) agree only on 58% of the claims.

Will add a human-labelled expected response and measure against it in a follow up research. This one only captures the disagreement between the models, but not which model is write…

The reason for the "No explanations, no qualifiers" in the prompt was to force the models to put the claim in one of the four buckets and answer with the bucket name only. It's a p…

@john_strinlai @gcr, depends on the application. In many cases an "I don't know" answer is indeed better than a forced answer. But in many production systems, LLMs generate content…

Search was enabled for 2 of the 5 models -- Gemini and Sonar Pro. The disagreement between them is still high - different verdict on 42% of the claims. Fully agree, that some of th…

Two of the five models used (Gemini+Search and Sonar Pro) have retrieval capabilities and used search when classifying the claims. The disagreement between them is still quite sign…

Indeed. I prompted each model ones, plus one retry on errors. Very good point to measure the inter-model disagreement! Will add in the next version. Section "4.2 Agreement w/ peer …