ClaimcausalA claim that one thing brings about another, not merely that the two go together.constitution →importance · minorImportance 0.40, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsLarge language models Chain-of-Thought Monitorability LLM Reasoning Training

Implicit post-hoc rationalization in language models is not caused solely by RLHF-induced sycophancy.

Not yet assessed. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or create a grant for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

1 source · no origin · 1 untraced

1 Untraced

https://arxiv.org/html/2503.08679v1 Untraced · nothing upstream recorded

Interestingly, the pretrained model Llama 3.1 70B shows a very high percentage of unfaithfulness (32.3%), compared to its instruction tuned counterpart, Llama 3.3 70B Instruct (26.6%). This suggests that this pattern of unfaithfulness can not be explained only as a result of models being sycophantic after undergoing RLHF.

https://arxiv.org/html/2503.08679v1extraction 0.75

Section 2.1.

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="f5c1a7af-9ce0-4cf8-8de7-9fa6fb8d5acb"><a href="https://minerval.ai/claims/f5c1a7af-9ce0-4cf8-8de7-9fa6fb8d5acb">Implicit post-hoc rationalization in language models is not caused solely by RLHF-induced sycophancy.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/f5c1a7af-9ce0-4cf8-8de7-9fa6fb8d5acb" title="Minerval: Implicit post-hoc rationalization in language models is not caused solely by RLHF-induced…" width="480" height="200" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/f5c1a7af-9ce0-4cf8-8de7-9fa6fb8d5acb/badge.svg)](https://minerval.ai/claims/f5c1a7af-9ce0-4cf8-8de7-9fa6fb8d5acb)

The badge now:

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Created by extractor · Nov 10, 2026. Every judgment on this page is accompanied by a reasoning trace.