Challenge: Existing studies evaluate only the final predicted answer of a puzzle, without providing any finer metrics to evaluate them.
Approach: They propose to use a grid-based evaluation dataset to evaluate LLMs' reasoning abilities and a new error taxonomy to evaluate their reasoning chains.
Outcome: The proposed model outperforms existing prompting methods on a wide range of natural language understanding tasks previously thought to be exclusive to humans.

Similar Papers

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing work investigating the logical reasoning ability of large language models has focused only on a couple of inference rules of propositional and first-order logics.
Approach: They propose to use a natural language question-answering dataset to evaluate the logical reasoning ability of large language models.
Outcome: The proposed model performs poorly on a range of natural language questions using chain-of-thought prompting.
Evaluating Step-by-step Reasoning Traces: A Survey (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation practices are inconsistent, resulting in fragmented progress across evaluator design and benchmark development.
Approach: a survey provides a comprehensive overview of step-by-step reasoning evaluation . existing evaluation practices are inconsistent, resulting in fragmented progress .
Outcome: The proposed evaluation criteria are based on four top-level categories . the results are presented in a systematic review of the literature.
FineReason: Evaluating and Improving LLMs’ Deliberate Reasoning through Reflective Puzzle Solving (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) highlight an important shift from the “System 1” way of quick reactions to the “system 2” style of reflection-and-correction problem solving.
Approach: They propose a logic-puzzle benchmark for systematic evaluation of large language models' reasoning capabilities that decomposes each puzzle into atomic steps.
Outcome: The proposed model improves on state checking and state transition tasks and demonstrates gains in reasoning by up to 5.1%.
Assessing LLM Reasoning Steps via Principal Knowledge Grounding (2025.findings-emnlp)

Copied to clipboard

Challenge: Step-by-step reasoning has become a standard approach for large language models to tackle complex tasks.
Approach: They propose a framework that assesses the knowledge grounding of intermediate reasoning by using a large-scale repository of atomic knowledge essential for reasoning.
Outcome: The evaluation suite identifies missing or misapplied knowledge elements and provides crucial insights for uncovering fundamental reasoning deficiencies in LLMs.
Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to eliminate implicit biases in LLMs do not eradicate underlying behavioral bias.
Approach: They propose a framework that uses logic grid puzzles to probe the influence of social stereotypes on logical reasoning and decision making in LLMs.
Outcome: The proposed framework systematically probes the influence of social stereotypes on logical reasoning and decision making in LLMs.
Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Large Reasoning Models (LRMs) often display unstable behaviors, e.g., hallucinating unsupported premises, overthinking simple tasks, and displaying higher sensitivity to prompt variations.
Approach: They propose a graph-based analytical framework that clusters long, verbose CoT outputs into semantically coherent reasoning steps, then constructs directed reasoning graphs to capture contextual and logical dependencies among these steps.
Outcome: The proposed framework enables quantitative evaluation of internal reasoning structure and quality beyond conventional metrics and provides practical insights for prompt engineering and cognitive analysis of LLMs.
RAFFLES: Reasoning-based Attribution of Faults for LLM Systems (2026.eacl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks focus on simple metrics and end-to-end outcomes, but they struggle with longer contexts.
Approach: They propose an offline evaluation architecture that incorporates iterative reasoning to evaluate the quality of the candidate faults and rationales of the Judge.
Outcome: The proposed architecture outperforms baseline evaluation frameworks with two datasets to identify step-level faults in multi-agent systems and ReasonEval datasets.
Puzzle Solving using Reasoning of Large Language Models: A Survey (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have demonstrated their logical reasoning abilities across various domains.
Approach: They propose to divide puzzles into rule-based and rule-less categories and critically assess LLMs' performance through various methodologies.
Outcome: The proposed models have demonstrated capabilities in deductive reasoning and inductive reasoning, but they face limitations in inductive thinking.
Exposing the Achilles’ Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing evaluations focus on final accuracy, neglecting the critical aspect of reasoning capabilities.
Approach: They propose to evaluate LLMs’ abilities to detect and correct reasoning mistakes by using rule-based methods and smaller language models.
Outcome: The proposed model outperforms existing models such as GPT-4o and GPT4 in both accuracy and accuracy, but lacks data contamination and memorization concerns.
SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas (2025.emnlp-main)

Copied to clipboard

Challenge: SATBench is a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SAT) problems.
Approach: They propose a benchmark to evaluate logical reasoning capabilities of large language models (LLMs) using logical puzzles derived from Boolean satisfiability problems.
Outcome: The proposed model achieves 65.0% accuracy on hard UNSAT problems, close to the baseline of 50%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations