trailTasks requiring long serial reasoning force language models to externalize reasoning in chain of thought.
When chain-of-thought reasoning is necessary for a task, language models struggle to evade chain-of-thought monitors.
Models are more likely to reveal misbehavior in their chain of thought when the misbehavior requires multi-step reasoning.
Argument from bounded per-token serial depth· for
Constant-depth transformers without chain of thought are limited to TC0 on inherently serial tasks.
atomic
Chain-of-thought prompting substantially improves language-model accuracy, primarily on mathematical and symbolic multi-step tasks.
atomic
Models almost always reveal in chain of thought their use of cues that require chain-of-thought reasoning.
atomic
Argument from encoded or non-legible intermediate tokens· against
Language models can perform multi-step reasoning using non-legible intermediate tokens.
Language models can learn to reason step by step in human-illegible encoded formats.
Transformers trained with dense supervision can use meaningless filler tokens to solve algorithmic tasks they cannot solve without intermediate tokens.
Penalizing specific chain-of-thought content leads language models to encode that reasoning steganographically.
Outcome-based reinforcement learning can make some reasoning models' chains of thought illegible.
shared · shown elsewhere
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Tasks requiring long serial reasoning force language models to externalize reasoning in chain of thought.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.75Credence, from 0 to 1: the Steward's probability that the claim, as stated, is true. Stated only where a single number is an honest summary; normative and evaluative claims usually carry none.constitution →
2depended on by
this rests on ↓
claimA box is a claim: a single proposition the graph assesses, with its own page and map. Click any claim to centre the map on it.constitution →quantityA box with a rule beneath its text is a quantity: a value the graph estimates rather than a proposition it affirms or denies. Its estimate stands where a claim's status would.constitution →questionA rounded box is a question: answered rather than affirmed or denied, with its candidate answers, subquestions and presuppositions beneath it. Its mark says how well answered it is.constitution →argumentA pill is an argument: one line of reasoning stating how the claims beneath it combine to bear on the claim above it, for or against. Arguments are not destinations; click their claims to explore.constitution →✓verifiedThe evidence, examined directly, establishes the claim.constitution →↑supportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →⇄inconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →↓doubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →✕contradictedThe evidence, examined directly, weighs against the claim.constitution →?unknownInsufficient information to assess.constitution →◌unassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →verified factunsettledvalue premisetheoremprizeA double ring marks a claim with a live prize: an amount in owls offered for a machine-checked proof or disproof of its published formal statement. The amount is in the preview and on the claim page; a prize changes nothing about how the claim is assessed or how important it is judged to be.prize rules →⊢machine-checked⊢ marks a claim whose published formal statement has a machine-checked proof or disproof. The checker confirms the proof; the verdict beside it is still the steward's judgment of the claim as worded.prize rules →supportsthis provides evidence for the parentsteward instructions →contradictsthis argues against the parentsteward instructions →assumesbackground the parent's framing takes as givensteward instructions →requiresa load-bearing premise: the parent is false without itsteward instructions →answersa candidate answer to the questionconstitution →Fig. Detail falls off with distance; every claim is an address.