REVIEW 8 cited by
JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models
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
Logical reasoning is a critical component of Large Language Models (LLMs), and substantial research efforts in recent years have aimed to enhance their deductive reasoning capabilities. However, existing deductive reasoning benchmarks, which are crucial for evaluating and advancing LLMs, are inadequate due to their lack of task complexity, presence of prior knowledge as a confounder, and superficial error analysis. To address these deficiencies, we introduce JustLogic, a synthetically generated deductive reasoning benchmark designed for rigorous evaluation of LLMs. JustLogic is (i) highly complex, capable of generating a diverse range of linguistic patterns, vocabulary, and argument structures; (ii) prior knowledge independent, eliminating the advantage of models possessing prior knowledge and ensuring that only deductive reasoning is used to answer questions; and (iii) capable of in-depth error analysis on the heterogeneous effects of reasoning depth and argument form on model accuracy. Our experimental results on JustLogic reveal that (i) state-of-the-art (SOTA) reasoning LLMs perform on par or better than the human average but significantly worse than the human ceiling, and (ii) SOTA non-reasoning models still underperform the human average. All code and data are available at https://github.com/michaelchen-lab/JustLogic
Forward citations
Cited by 8 Pith papers
-
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
Chat UI and API access to the same chatbot produce different accuracy, consistency, citation, and refusal behaviors on safety benchmarks, and web search changes these patterns further.
-
Abductive Corroboration of Probabilistic AI Models for Forensic Synthetic Media Detection
Multi-detector corroboration reduces FP/TP from ~0.22 to 0.02 (two models) or 0 (three models) while first measuring OpenAI SynthID production rollout and detector complementarity.
-
ReportLogic: Evaluating Logical Quality in Deep Research Reports
An auditability-based benchmark with three logic layers and eight dimensions shows a distilled judge agrees with human experts ~74-75% versus ~62-74% for frontier LLM judges.
-
Deductive Logic in Language Models: Horizontal vs Vertical Reasoning
A 2-layer, single-head attention-only transformer learns to perform multi-step logical deduction through induction-head circuits for rule completion, chaining, and final decision.
-
Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL
DRER rewards CoT trajectories that increase the model's likelihood of the correct answer, plus a length penalty, and the new LogicTree benchmark reportedly lifts a 7B model's average accuracy from 0.13 to 0.60.
-
PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data
A DSL plus SMT solver generates and validates 83,657 logic puzzles, and fine-tuning on them improves a 7B model's scores on several reasoning benchmarks.
-
Logical Reasoning with Outcome Reward Models for Test-Time Scaling
Outcome reward models trained on multi-sample chain-of-thought plus deliberately flawed 'echo' rationales improve Best-of-N test-time verification for deductive reasoning.
-
Improving Large Language Models with Concept-Aware Fine-Tuning
Adding lightweight multi-token auxiliary heads with a weighted future-token loss improves supervised fine-tuning of Llama-3-8B-Instruct across five diverse tasks.
Discussion (0). Sign in to comment.