Skip to content

Are Stated Reasoning Steps Causally Load-Bearing?

Sep 2026 · arXiv.org · Vol abs/2609.27038 · 0 citations · 12 references
Computer Science

TL;DR

This work uses synthetic multi-hop lookup tasks to measure faithfulness causally at the activation level, specifically on self-generated reasoning, and aims to measure faithfulness causally at the activation level, specifically on self-generated reasoning.

Abstract

Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer. Previous faithfulness metrics have been predominantly behavioral, as they simply edit the reasoning text and observe the resulting answer. However, our methodology aims to measure faithfulness causally at the activation level, specifically on self-generated reasoning. Unlike previous causal audits, which measure degradation, our interventions carry a known predicted target. In this way, each patch should switch the answer to a specific counterfactual entity derivable by construction. Specifically, we use synthetic multi-hop lookup tasks (2-6 hops). We patch the residual stream at the token span where the model states each intermediate step with the corresponding activations from a counterfactual run. For Qwen3-4B, 76.9% +/- 2.8% of stated steps are causally load-bearing (CLB) at the most responsive mid-network layer (random-position null: 11.3%; patching the underlying prompt fact: 83%, so stated steps carry approximately 96% of the achievable effect). Moreover, the standard behavioral test on the same items yields 88.2%, which overstates causal faithfulness by 11.4 percentage points (item-matched; 111:14 discordant pairs, p<1e-15) and, for the easiest items, by up to 20 percentage points. This gap also has a clear capability dimension. Qwen3-1.7B is far less causally faithful overall (54.8%), with its faithfulness collapsing as reasoning depth increases (68% at 2 hops to 30% at 6), while Qwen3-4B remains relatively flat. Although stated reasoning can be causally meaningful, standard behavioral tests tend to overestimate its causal faithfulness, particularly on easier examples where model reasoning appears most fluent.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought

Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch intervention that perturbs one reasoning step, truncates the chain, and forces the model to continue from the corrupted prefix. It measures how load...

Renee Jia, Di Mu · 0 citations

REALHOP: Rethinking Multi-Hop Reasoning Evaluation via Behavioral Auditing

Results show that a conceptually coherent chain and a correct final answer do not by themselves establish multi-hop reasoning, and introduce REALHOP, a diagnose-construct-verify framework that rebinds entities, factorizes selected relations, adds complete competing paths, and places evidence at traceable locations.

Ji-Hua Tao, Xiao-Kun Yuan, Yao-Ming Li et al. · 0 citations
#artificial intelligence Preprint Sep 2026

LLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator

Step-level reasoning evaluators are commonly based on autoregressive language models, whose causal attention restricts each step representation to the problem, previous steps, and the current step. Yet, when the complete solution is available, the validity of an earlier step may become clearer only through its downstre...

Yi-Ming Feng, Nai-Hao Deng, Yu-Long Chen et al. · 0 citations

State of Thought Enables Endogenous Reasoning

State of Thought is proposed, a new reasoning paradigm that enables endogenous reasoning in LLMs, with the model's internal reasoning state governing how reasoning unfolds, and provides a generalizable and efficient alternative to existing test-time reasoning paradigms.

Z. Gong, Yi-Kun Hou, Zi-Hao Zeng et al. · 0 citations
#artificial intelligence Preprint Aug 2026

The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning

The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing, and what works is reconstructing the whole steered activation with those dimensions pinned to their natural values.

Dylan Jayabahu, Tinuade Adeleke · 0 citations
#machine learning Preprint Sep 2026

Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning

This work operationalizes the importance of a reasoning step as its advantage: the change in expected reward, e.g., producing the correct final answer, from including that step, estimated via Monte Carlo rollouts, and evaluates whether LLM judges can identify high-advantage steps and finds that sufficiently capable LLM...

Kevin Du, A. Hoyle, L. Ruis et al. · 1 citation

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.