REVIEW 6 cited by
Faithful Logical Reasoning via Symbolic Chain-of-Thought
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
While the recent Chain-of-Thought (CoT) technique enhances the reasoning ability of large language models (LLMs) with the theory of mind, it might still struggle in handling logical reasoning that relies much on symbolic expressions and rigid deducing rules. To strengthen the logical reasoning capability of LLMs, we propose a novel Symbolic Chain-of-Thought, namely SymbCoT, a fully LLM-based framework that integrates symbolic expressions and logic rules with CoT prompting. Technically, building upon an LLM, SymbCoT 1) first translates the natural language context into the symbolic format, and then 2) derives a step-by-step plan to solve the problem with symbolic logical rules, 3) followed by a verifier to check the translation and reasoning chain. Via thorough evaluations on 5 standard datasets with both First-Order Logic and Constraint Optimization symbolic expressions, SymbCoT shows striking improvements over the CoT method consistently, meanwhile refreshing the current state-of-the-art performances. We further demonstrate that our system advances in more faithful, flexible, and explainable logical reasoning. To our knowledge, this is the first to combine symbolic expressions and rules into CoT for logical reasoning with LLMs. Code is open at https://github.com/Aiden0526/SymbCoT.
Forward citations
Cited by 6 Pith papers
-
Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes
ReFine combines rule-guided prompting and dual-granularity filtering to improve LLM-based tabular data generation when only 30 to 90 labeled rows exist, achieving top average rank over baselines.
-
LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs
LogiPlan introduces a three-task benchmark with controllable graph complexity, showing that although reasoning models excel at plan generation, all models degrade sharply on cycle detection and deep comparison questions.
-
Learning to Reason via Mixture-of-Thought for Logical Reasoning
Jointly training and voting across natural language, code, and truth-table reasoning modalities improves LLM logical reasoning accuracy by up to 11.7 percentage points.
-
Blueprint First, Model Second: A Framework for Deterministic LLM Workflow
A source-code-driven 'blueprint first' agent framework reports strong τ-bench results, but the paper contains an abstract/body mismatch and releases no artifacts.
-
Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
A prompting method that alternates backward and forward reasoning improves small LLM accuracy on math and search tasks and reduces the number of visited search states.
-
Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality
A thesis that combines self-learning from dialog logs, schema-guided prompting, and self-aligned factuality to build task bots with minimal human intervention.
Discussion (0). Sign in to comment.