Pith. sign in

REVIEW 5 cited by

Symbolic Knowledge Distillation: from General Language Models to Commonsense 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

arxiv 2110.07178 v2 pith:IJEZZQAO submitted 2021-10-14 cs.CL

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models

classification cs.CL
keywords commonsensemodelsknowledgemodelgenerallanguagedistilldistillation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The common practice for training commonsense models has gone from-human-to-corpus-to-machine: humans author commonsense knowledge graphs in order to train commonsense models. In this work, we investigate an alternative, from-machine-to-corpus-to-machine: general language models author these commonsense knowledge graphs to train commonsense models. Our study leads to a new framework, Symbolic Knowledge Distillation. As with prior art in Knowledge Distillation (Hinton et al., 2015), our approach uses larger models to teach smaller models. A key difference is that we distill knowledge symbolically-as text-in addition to the neural model. We also distill only one aspect-the commonsense of a general language model teacher, allowing the student to be a different type, a commonsense model. Altogether, we show that careful prompt engineering and a separately trained critic model allow us to selectively distill high-quality causal commonsense from GPT-3, a general language model. Empirical results demonstrate that, for the first time, a human-authored commonsense knowledge graph is surpassed by our automatically distilled variant in all three criteria: quantity, quality, and diversity. In addition, it results in a neural commonsense model that surpasses the teacher model's commonsense capabilities despite its 100x smaller size. We apply this to the ATOMIC resource, and share our new symbolic knowledge graph and commonsense models.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Reasoning with Language Model is Planning with World Model

    cs.CL 2023-05 unverdicted novelty 6.0

    RAP turns LLMs into dual world-model and planning agents via MCTS to generate better reasoning paths, outperforming CoT baselines and achieving 33% relative gains over GPT-4 CoT using LLaMA-33B on plan generation.

  2. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

    cs.CL 2023-05 conditional novelty 6.0

    Distilling step-by-step uses LLM-generated rationales as additional supervision in a multi-task framework so that 770M-parameter models outperform 540B-parameter models on NLP benchmarks with only 80% of the data.

  3. AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions

    cs.AI 2026-06 unverdicted novelty 5.0

    AgentTrust v2 deploys an LLM judge with self-learning on semantic attacks to raise accuracy from 48% to 83.6-85.2% while distilling rules and using guarded RAG, cutting judge calls and eliminating benign blocks over 4...

  4. Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt

    cs.CL 2026-06 unverdicted novelty 5.0

    Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.

  5. Overmind NSA: A Unified Neuro-Symbolic Computing Architecture with Approximate Nonlinear Activations and Preemptive Memory Bypass

    cs.AR 2026-04 unverdicted novelty 4.0

    Overmind is a neuro-symbolic architecture that uses adjustable Padé approximations and memory bypass to deliver 8.1 TOPS/W efficiency and 410 GOPS throughput on mixed workloads with minimal accuracy loss.