# DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning

arXiv: https://arxiv.org/abs/2504.07080 · HTML: https://mlsanity.com/paper/2504.07080/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples](https://mlsanity.com/paper/2305.15269/) (2023)
- [Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap](https://mlsanity.com/paper/2402.19450/) (2024)
- [LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2404.15522/) (2024)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation](https://mlsanity.com/paper/2312.17080/) (2023)
- [Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2402.08955/) (2024)
- [Evaluating the Robustness of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2411.14215/) (2024)
- [Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning](https://mlsanity.com/paper/2406.10834/) (2024)
- [Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability](https://mlsanity.com/paper/2411.19456/) (2024)

## Built on by (most cited first, 1 of 1)

- [Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency](https://mlsanity.com/paper/2602.16787/) (2026)

## Abstract (arXiv)

Despite great performance on Olympiad-level reasoning problems, frontier large language models can still struggle on high school math when presented with novel problems outside standard benchmarks. Going beyond final accuracy, we propose a deductive consistency metric to analyze chain-of-thought output from language models (LMs).Formally, deductive reasoning involves two subtasks: understanding a set of input premises and inferring the conclusions that follow from them. The proposed metric studies LMs' performance on these subtasks, with the goal of explaining LMs' reasoning errors on novel problems: how well do LMs understand input premises with increasing context lengths, and how well can they infer conclusions over multiple reasoning hops? Since existing benchmarks may be memorized, we develop a pipeline to evaluate LMs' deductive consistency on novel, perturbed versions of benchmark problems. On novel grade school math problems (GSM-8k), we find that LMs are fairly robust to increasing number of input premises, but suffer significant accuracy decay as the number of reasoning hops is increased. Interestingly, these errors are masked in the original benchmark as all models achieve near 100% accuracy. As we increase the number of solution steps using a synthetic dataset, prediction over multiple hops still remains the major source of error compared to understanding input premises. Other factors, such as shifts in language style or natural propagation of early errors do not explain the trends. Our analysis provides a new view to characterize LM reasoning -- as computations over a window of input premises and reasoning hops -- that can provide unified evaluation across problem domains.