SYNTHESIS NOTE
Topics›Reasoning Logic Internal Rules›this note

What three separate factors drive chain-of-thought performance?

Can we isolate and measure the distinct contributions of output probability, memorization, and genuine reasoning to CoT success? Understanding their relative weights matters for knowing when CoT actually reasons versus when it relies on shortcuts.

Synthesis note · 2026-02-22 · sourced from Reasoning Logic Internal Rules

The "Deciphering Factors Influencing CoT" paper achieves something rare: a clean decomposition of what drives Chain-of-Thought performance into three independently measurable factors, using the simple but controlled task of shift cipher decoding across GPT-4, Claude 3, and Llama 3.1.

Factor 1: Output probability. The probability of the correct output in the model's distribution dramatically affects CoT accuracy. Varying only the output's probability of occurrence shifts GPT-4 accuracy from 26% to 70%. CoT works better when the answer is already more probable — it amplifies existing tendencies rather than overcoming them.

Factor 2: Memorization. Performance is higher when the specific cipher variant was more frequently encountered during pre-training. This is not reasoning — it is pattern matching against memorized instances. The frequency of encountering different shift values in training data directly predicts accuracy on those shifts.

Factor 3: Noisy reasoning. After controlling for probability and memorization, genuine reasoning effects remain — but they are noisy. Error rate increases with the number of implicit reasoning steps (shift magnitude). This is real multi-step reasoning, but each step introduces error probability, so accuracy degrades with chain length.

The decomposition resolves the ongoing debate about whether LLMs reason or memorize: they do both, simultaneously, and the contribution of each factor varies by task. This supports Does chain-of-thought reasoning reveal genuine inference or pattern matching? while adding a crucial nuance: the imitation IS partially genuine, but contaminated by probability bias and memorization artifacts.

The probability factor is particularly important for understanding CoT faithfulness. Since Do language models actually use their reasoning steps?, the probability dependence reveals a specific mechanism for causal insufficiency: CoT "reasoning" succeeds partly because the sequence of generated tokens increases the conditional probability of the correct answer, not because the logical content is being processed. This is exactly the mechanism behind Does logical validity actually drive chain-of-thought gains? — invalid exemplars work because they still generate token sequences that shift output probability toward correct answers.

The noisy-reasoning factor connects to Does more thinking time always improve reasoning accuracy?: if each reasoning step adds noise, then past some threshold the accumulated noise exceeds the signal, producing the inverted-U performance curve.

Inquiring lines that read this note 74

This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.

Can AI systems evade safety evaluations through reasoning manipulation? Does chain-of-thought reasoning reveal how models actually think or merely imitate reasoning? Why does polished AI output gain credibility despite fundamental verifiability problems? What prevents LLMs from applying their reasoning knowledge to improve outputs? How do thinking tokens exhibit diminishing returns in reasoning? How does decomposing tasks into separate stages affect reasoning quality and safety? Can reasoning traces reveal actual model reasoning versus plausible output? How do interpretive frames override surface features in text comprehension? Why do training associations persist despite contradictory contextual information? Can latent reasoning match or exceed explicit reasoning performance? Do accumulated memories help or hurt continual learning in models? Can language models reliably simulate personas and predict behavior? What are the fundamental limits of prompting for language models? When does parallel reasoning outperform sequential reasoning with the same token budget? What makes agent memory systems durable and reusable across sessions? Can reasoning models use reflection to correct their initial outputs? What makes process supervision effective for training complex reasoning models? What limits language model accuracy in evaluating ideas? How do users confuse explanation quality with actual system accuracy? What prediction granularity best trains models to generate reliable reasoning? How do reward signal properties affect model reasoning and safety? Do individually safe AI actions create unsafe outcomes in integrated systems? Why do autonomous agents misreport success on failed actions? What explains the gap between benchmark scores and true reasoning capability? Does scaling reasoning capability create fundamental tradeoffs in control and reliability? How do curriculum design and feedback approaches affect model learning? Does reinforcement learning create genuinely new reasoning capabilities or only refine existing ones? Do single-axis benchmarks accurately measure agent capability for real deployment? Should models ask for clarification when facing ambiguous or under-specified information? How does diversity prevent model convergence on superficial patterns? How do transformer attention patterns implement retrieval and reasoning? How do individually-safe actions create collectively-unsafe outcomes? Can models strategically underperform during evaluation to hide capabilities? Does AI assistance help or harm professional skill development? How should agents coordinate through shared persistent code artifacts? Can confidence signals reliably detect flawed reasoning in language models? How can humans maintain effective oversight as AI systems scale? How does model capacity affect learning performance on diverse downstream tasks?

Related concepts in this collection 6

This note in its neighbourhood — explore the map, then jump to a related concept in the list below.

Concept map
13 direct connections · 136 in 2-hop network ·dense cluster Open in graph ↗
What three separate factors drive chain-of-thoug… Does chain-of-thought reasoning reveal genuine inf… Do language models actually use their reasoning st… Does logical validity actually drive chain-of-thou… Does more thinking time always improve reasoning a… Do reasoning traces need to be semantically correc… What do models actually learn from chain-of-though…

Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph

your link semantically near linked from elsewhere

Related papers in this collection 8

Papers most semantically related to this note, ranked by cosine similarity in the embedding space.

Search by related questions 4

Suggested questions this note speaks to — click to search the collection, or type your own.

Does each reasoning step in chain-of-thought introduce cumulative error?Why do logically invalid chain-of-thought examples work nearly as well?Can chain-of-thought faithfulness exist without causal necessity in reasoning?How much does pre-training frequency predict reasoning task performance?
Original note title

cot performance reflects three disentangled factors — output probability memorization and noisy reasoning