Glowing network of connections through douglas fir roots
3 min read
Preprint

Does the Evidence a Model Cites Drive Its Conclusion? Our preprint is out

By Darren Brewster and Barry SevigPublished

When a language model writes down its reasoning, does the evidence it cites actually drive the conclusion it states? That is the question our new preprint asks. The paper is available on Zenodo at DOI 10.5281/zenodo.23308620.

What we did

We ran a pre-registered causal test of declared evidence relations in Scholialang reasoning traces, on Qwen2.5-7B-Instruct, using a controlled comparison task. In Scholialang a model emits typed, machine-checkable traces in which a Finding atom declares its dependence on an Evidence atom. We tested that declared edge with activation patching: we spliced a counterfactual Evidence span's activations into the clean context and checked whether the Finding's read was redirected the way the relation predicts.

What we found

For this model and task, a model's emitted symbolic label can causally steer its subsequent conclusion, even when the accompanying facts disagree.

Flipping only the polarity label (supports/refutes) redirected the conclusion in 73 of 90 relations. Swapping only the numbers never changed the selected status under this intervention, although in a post-hoc analysis it shifted the decision margin toward the counterfactual status in every case. What we establish is downstream label influence.

The metric was validated on cases where task relevance is known by construction. Under the pre-registered protocol it separated relevant from irrelevant evidence perfectly (J = 1.0 in both evidence orders). On two batteries, patching the cited evidence redirected the conclusion in 77/90 and 53/71 relations, roughly 75 to 86 percent, with substantial variance between batteries. Unrelated-evidence controls never redirected.

What it does not show

We have not shown that the method detects genuine unfaithfulness. Behavioral arms on two hosted models were direction-sensitive to their own evidence edits, but an authority-cue arm induced no unfaithfulness for the method to catch. The results are on an open 7B model and synthetic test cases. Where the numeric comparison is computed, and whether the declared reference structure itself controls routing, remain open: we did not intervene on how the label was generated.

Why it matters

Reasoning that software depends on needs to be checkable, not just readable. A trace that declares "this finding depends on that evidence" is making a claim about the model's computation. This paper describes one reproducible way to test such a claim, and reports what we found when we did.

Brewster, D. and Sevig, B. (2026). Does the Evidence a Model Cites Drive Its Conclusion? A Pre-registered Causal Test of Declared Evidence Relations in Structured Reasoning Traces. Zenodo. DOI: 10.5281/zenodo.23308620

More from Doug Fir Labs

Reasoning protocol graph woven through douglas fir roots

Reasoning Needs a Protocol Layer

Scholialang helps agentic systems preserve reasoning state, use tools without quality loss, and reduce context cost across long-horizon work — a durable protocol for claims, evidence, decisions, contradictions, and verification across agents.

Product Release6 min readRead
Forest canopy aerial

Why Neuro-Symbolic Architecture Is the Missing Layer in LLM Infrastructure

Large language models are powerful pattern matchers, but pattern matching alone doesn't constitute reasoning. We explore how composing symbolic reasoning primitives with neural inference creates models that are more capable, auditable, and trustworthy.

Research7 min readRead