# Commonsense on Demand: Generating and Selectively Integrating Commonsense Knowledge for Natural Language Inference

arXiv: https://arxiv.org/abs/2507.15100 · HTML: https://mlsanity.com/paper/2507.15100/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 20 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Sources of Hallucination by Large Language Models on Inference Tasks](https://mlsanity.com/paper/2305.14552/) (2023)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches](https://mlsanity.com/paper/1904.01172/) (2019)
- [Neural Natural Language Inference Models Enhanced with External Knowledge](https://mlsanity.com/paper/1711.04289/) (2017)
- [RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms](https://mlsanity.com/paper/2005.00782/) (2020)
- [ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference](https://mlsanity.com/paper/2108.01589/) (2021)

## Abstract (arXiv)

Natural Language Inference (NLI) determines whether a premise entails, contradicts, or is neutral with respect to a hypothesis. The task is often framed as emulating human inference, in which commonsense knowledge plays a major role. This study examines whether Large Language Models (LLMs) can reliably generate factual commonsense axioms for NLI, and evaluates their utility on the SNLI and ANLI benchmarks using Llama-3.1-70B and gpt-oss-120b. Because commonsense axioms lack explicit textual references, standard factuality metrics are ill-suited to their evaluation. We therefore introduce a reference-free method using an LLM-as-Judge framework. The evaluation reveals a substantial gap between models: gpt-oss-120b generates predominantly accurate axioms, whereas Llama produces more incorrect than correct ones. We further evaluate three prompting pipelines: direct inference, inference augmented with generated commonsense axioms, and a hybrid approach that selectively incorporates highly factual axioms based on judged factuality. The hybrid approach yields consistent accuracy gains of 3.87%-8.5% across tested configurations. Targeted commonsense knowledge also helps models overcome a bias toward the Neutral class by providing essential real-world context.