REVIEW 6 cited by
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
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
Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory has not yet been demonstrated, and methods for reconstructing proofs of answers are imperfect. In this work we show that a generative model, called ProofWriter, can reliably generate both implications of a theory and the natural language proof(s) that support them. In particular, iterating a 1-step implication generator results in proofs that are highly reliable, and represent actual model decisions (rather than post-hoc rationalizations). On the RuleTaker dataset, the accuracy of ProofWriter's proofs exceed previous methods by +9% absolute, and in a way that generalizes to proof depths unseen in training and on out-of-domain problems. We also show that generative techniques can perform a type of abduction with high precision: Given a theory and an unprovable conclusion, identify a missing fact that allows the conclusion to be proved, along with a proof. These results significantly improve the viability of neural methods for systematically reasoning over natural language.
Forward citations
Cited by 6 Pith papers
-
Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?
Long chain-of-thought and RL training on math problems improves general reasoning benchmarks, while short chain-of-thought math fine-tuning often degrades performance.
-
Reasoning is about giving reasons
A transformer can convert reasoning sentences into a task-specific logical form with 95-99% exact match, after which a symbolic solver answers deductive queries.
-
Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training
Fine-tuning a 3B LLM on randomly symbolized reasoning questions reduces spurious-correlation failures and improves OOD accuracy on CLadder and PrOntoQA.
-
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration
A linear probe over layer-wise logit-lens probabilities ranks LLM confidence well enough to slightly beat voting or probability-based baselines in QA ensembles.
-
Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System
SynergyMAS combines a graph database with a Clingo logic solver, corrective RAG, and Theory of Mind prompts in a hierarchical multi-agent team, demonstrated on a Smart Home Energy Management case study.
-
Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
A 4B-parameter model is claimed to explain its own reasoning through inverse attention analysis, but the paper offers no consistent evidence or artifacts.
Discussion (0). Continue with ORCID to comment.