SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification

Hugging Face Daily Papers Papers

Summary

SymDiag is a neuro-symbolic framework that translates chain-of-thought reasoning into symbolic constraints and performs step-level satisfiability checks to localize failures in LLM reasoning, disentangling translation errors from reasoning errors.

Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers are correct. Most existing ``verification'' signals are not diagnostic: answer matching observes only the outcome, LLM-as-judge provides subjective and non-verifiable critiques, and scalar rewards (e.g., PRMs/RMs) offer little insight into where a multi-step derivation fails.We propose SymDiag, a neuro-symbolic framework that reframes reasoning verification as structured failure diagnosis. SymDiag translates natural-language CoT into symbolic constraints and performs step-level satisfiability/entailment checks to (i) localize failing steps and (ii) produce verifiable diagnostic evidence, including counterexamples, inconsistency witnesses, and missing-premise indicators. A central challenge is that apparent ``logic violations'' can be caused either by genuine reasoning defects or by neural-to-symbolic translation noise. SymDiag therefore incorporates a Self-Auditor that disentangles TranslationError from ReasoningError via dual symbolic encodings consistency checks, enabling robust diagnosis under partial observability. Across diverse mathematical, logical, scientific, and general reasoning benchmarks, SymDiag improves detection of unfaithful reasoning and provides substantially more effective feedback for multi-round reasoning repair than outcome-only verification and LLM-based judging, offering a principled foundation for trustworthy and scalable reasoning diagnosis.
Original Article
View Cached Full Text

Cached at: 08/12/26, 08:23 AM

Paper page - SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification

Source: https://huggingface.co/papers/2608.08786

Abstract

SymDiag reframes reasoning verification as structured failure diagnosis by translating chain-of-thought into symbolic constraints, performing step-level satisfiability checks, and disentangling translation errors from reasoning errors to provide verifiable diagnostic evidence.

Large language models (LLMs) increasingly serve as data-driven reasoners, yet theirchains-of-thought(CoT) can be unfaithful even when final answers are correct. Most existing ``verification’’ signals are not diagnostic: answer matching observes only the outcome, LLM-as-judge provides subjective and non-verifiable critiques, and scalar rewards (e.g., PRMs/RMs) offer little insight into where a multi-step derivation fails.We propose SymDiag, aneuro-symbolic frameworkthat reframes reasoning verification as structured failure diagnosis. SymDiag translates natural-language CoT intosymbolic constraintsand performs step-levelsatisfiability/entailmentchecks to (i) localize failing steps and (ii) produce verifiable diagnostic evidence, includingcounterexamples,inconsistency witnesses, andmissing-premise indicators. A central challenge is that apparent ``logic violations’’ can be caused either by genuine reasoning defects or by neural-to-symbolic translation noise. SymDiag therefore incorporates aSelf-Auditorthat disentanglesTranslationErrorfromReasoningErrorviadual symbolic encodingsconsistency checks, enabling robust diagnosis under partial observability. Across diverse mathematical, logical, scientific, and general reasoning benchmarks, SymDiag improves detection of unfaithful reasoning and provides substantially more effective feedback for multi-round reasoning repair than outcome-only verification and LLM-based judging, offering a principled foundation for trustworthy and scalable reasoning diagnosis.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.08786

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.08786 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.08786 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.08786 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making

arXiv cs.AI

Researchers from the University of Michigan introduce MechSim, a mechanism-grounded neuro-symbolic reasoning framework that enables LLM agents to reason about the internal assumptions, dependencies, and execution behavior of scientific simulators rather than treating them as black boxes. The framework improves explanation quality and decision-making reliability across high-stakes domains like healthcare, finance, and public policy.

Logic-Regularized Verifier Elicits Reasoning from LLMs

arXiv cs.CL

Introduces LoVer, an unsupervised verifier that uses logical rules (negation consistency, intra-group and inter-group consistency) to improve LLM reasoning without labeled data, achieving performance close to supervised verifiers on reasoning benchmarks.