# Natural Language Deduction with Incomplete Information

arXiv: https://arxiv.org/abs/2211.00614 · HTML: https://mlsanity.com/paper/2211.00614/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 1 Nov 2022.

## Builds on (most cited first, 30 of 34)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark](https://mlsanity.com/paper/2103.13009/) (2021)
- [Generating Natural Language Proofs with Verifier-Guided Search](https://mlsanity.com/paper/2205.12443/) (2022)
- [Multi-hop Question Answering via Reasoning Chains](https://mlsanity.com/paper/1910.02610/) (2019)
- [Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction](https://mlsanity.com/paper/1905.08511/) (2019)
- [Natural Language Deduction through Search over Statement Compositions](https://mlsanity.com/paper/2201.06028/) (2022)
- [Conversational Neuro-Symbolic Commonsense Reasoning](https://mlsanity.com/paper/2006.10022/) (2020)
- [Flexible Generation of Natural Language Deductions](https://mlsanity.com/paper/2104.08825/) (2021)
- [Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner](https://mlsanity.com/paper/2205.09224/) (2022)
- [A Word on Machine Ethics: A Response to Jiang et al. (2021)](https://mlsanity.com/paper/2111.04158/) (2021)

## Built on by (most cited first, 12 of 12)

- [LAMBADA: Backward Chaining for Automated Reasoning in Natural Language](https://mlsanity.com/paper/2212.13894/) (2022)
- [Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements](https://mlsanity.com/paper/2305.03695/) (2023)
- [BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information](https://mlsanity.com/paper/2306.07934/) (2023)
- [Language Models as Inductive Reasoners](https://mlsanity.com/paper/2212.10923/) (2022)
- [Logical Reasoning over Natural Language as Knowledge Representation: A Survey](https://mlsanity.com/paper/2303.12023/) (2023)
- [Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement](https://mlsanity.com/paper/2402.00745/) (2024)
- [Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models](https://mlsanity.com/paper/2504.01001/) (2025)
- [VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks](https://mlsanity.com/paper/2511.04662/) (2025)
- [SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs](https://mlsanity.com/paper/2402.10979/) (2024)
- [Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End](https://mlsanity.com/paper/2212.10522/) (2022)
- [Deductive Additivity for Planning of Natural Language Proofs](https://mlsanity.com/paper/2307.02472/) (2023)
- [InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding](https://mlsanity.com/paper/2509.16534/) (2025)

## Abstract (arXiv)

A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises. However, these methods can only make sound deductions when they follow from evidence that is given. We propose a new system that can handle the underspecified setting where not all premises are stated at the outset; that is, additional assumptions need to be materialized to prove a claim. By using a natural language generation model to abductively infer a premise given another premise and a conclusion, we can impute missing pieces of evidence needed for the conclusion to be true. Our system searches over two fringes in a bidirectional fashion, interleaving deductive (forward-chaining) and abductive (backward-chaining) generation steps. We sample multiple possible outputs for each step to achieve coverage of the search space, at the same time ensuring correctness by filtering low-quality generations with a round-trip validation procedure. Results on a modified version of the EntailmentBank dataset and a new dataset called Everyday Norms: Why Not? show that abductive generation with validation can recover premises across in- and out-of-domain settings.