# Explicit Inductive Inference using Large Language Models

arXiv: https://arxiv.org/abs/2408.14467 · HTML: https://mlsanity.com/paper/2408.14467/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 26 Aug 2024.

## Builds on (most cited first, 13 of 13)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [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)
- [Prompt Consistency for Zero-Shot Task Generalization](https://mlsanity.com/paper/2205.00049/) (2022)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [Multi-modal Latent Space Learning for Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2312.08762/) (2023)
- [Conceptual and Unbiased Reasoning in Language Models](https://mlsanity.com/paper/2404.00205/) (2024)
- [Probabilistic Models of Relational Implication](https://mlsanity.com/paper/1907.12048/) (2019)
- [On the Robustness of Reading Comprehension Models to Entity Renaming](https://mlsanity.com/paper/2110.08555/) (2021)
- [Entailment Graph Learning with Textual Entailment and Soft Transitivity](https://mlsanity.com/paper/2204.03286/) (2022)
- [Smoothing Entailment Graphs with Language Models](https://mlsanity.com/paper/2208.00318/) (2022)
- [Language Models Are Poor Learners of Directional Inference](https://mlsanity.com/paper/2210.04695/) (2022)

## Abstract (arXiv)

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to use the out-of-context truth label of H as a fragile proxy. In this paper, we propose a pipeline that exploits this bias to do explicit inductive inference. Our pipeline uses an LLM to transform a premise into a set of attested alternatives, and then aggregate answers of the derived new entailment inquiries to support the original inference prediction. On a directional predicate entailment benchmark, we demonstrate that by applying this simple pipeline, we can improve the overall performance of LLMs on inference and substantially alleviate the impact of their attestation bias.