AI News HubLIVE
Original source2 min read

Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution

Large language models produce chain-of-thought reasoning that appears logically sound but may not genuinely depend on its stated premises. This paper introduces interventional grounding audits, a black-box step-level test of premise dependency that substitutes a predicate in a single premise and checks for changes in the normalized conclusion of each reasoning step. Evaluated on ProntoQA with GPT-4o, the method achieves F1=0.806 for detecting proof-tree dependencies, significantly outperforming a self-consistency baseline (F1=0.343). Notably, 66% of correctly solved problems contain at least one step insensitive to a direct proof-tree dependency, revealing a 'right answer, wrong reasoning' signal.

SourcearXiv AIAuthor: Hironao Nakamura

-->

[Submitted on 11 Jul 2026]

Title:Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution

View a PDF of the paper titled Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution, by Hironao Nakamura

View PDF HTML (experimental)

Abstract:Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its target predicate with a fresh symbol, re-run the model, and check whether each reasoning step's normalized conclusion (canonical predicate form) changes. We evaluate on ProntoQA, a synthetic multi-hop deductive reasoning benchmark with gold proof trees, where step-level premise dependencies are known. Applied to 50 ProntoQA problems with GPT-4o, our method achieves F1 = 0.806 on detecting proof-tree dependencies (F1 = 0.885 on predicate-determining dependencies; Recall = 100%), significantly outperforming a self-consistency baseline (F1 = 0.343; 95% bootstrap CIs non-overlapping). We further identify that 66% of correctly-solved problems contain at least one aligned step insensitive to a direct proof-tree dependency under consistent substitution -- all involving entity-introduction premises, a documented blind spot of the consistent-substitution evaluator -- a "right answer, wrong reasoning" signal invisible to passive methods. All audit certificates, raw outputs, and reproduction scripts are available in a public GitHub repository, and we discuss scope limits beyond formal, parsable benchmarks.

Comments: Accepted at the ICLR 2026 Workshop on Logical Reasoning of Large Language Models (this https URL)

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Logic in Computer Science (cs.LO)

Cite as: arXiv:2607.13069 [cs.AI]

(or arXiv:2607.13069v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.13069

arXiv-issued DOI via DataCite

Submission history

From: Hironao Nakamura [view email] [v1] Sat, 11 Jul 2026 01:32:22 UTC (42 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution, by Hironao Nakamura

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-07

Change to browse by:

cs cs.CL cs.LO

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)