REVIEW 2 cited by
Boosting Deductive Reasoning with Step Signals In RLHF
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 crucial task for Large Language Models (LLMs), enabling them to tackle complex problems. Among reasoning tasks, multi-step reasoning poses a particular challenge. Grounded in the theory of formal logic, we have developed an automated method, Multi-step Deduction (MuseD), for deductive reasoning data. MuseD has allowed us to create training and testing datasets for multi-step reasoning. Our generation method enables control over the complexity of the generated instructions, facilitating training and evaluation of models across different difficulty levels. Through RLHF training, our training data has demonstrated significant improvements in logical capabilities for both in-domain of out-of-domain reasoning tasks. Additionally, we have conducted tests to assess the multi-step reasoning abilities of various models.
Forward citations
Cited by 2 Pith papers
-
Can VLMs Reason Robustly? A Neuro-Symbolic Investigation
End-to-end fine-tuned VLMs fail to induce reasoning functions under object-count covariate shifts; VLC (VLM concepts + circuits) yields consistently higher OOD accuracy.
-
Learning to Select In-Context Demonstration Preferred by Large Language Model
A generative preference-learning method trains a latent demonstration selector from LLM feedback and improves few-shot in-context learning performance on most of 19 benchmark datasets.
Discussion (0). Sign in to comment.