# Bonsai: Interpretable Tree-Adaptive Grounded Reasoning

arXiv: https://arxiv.org/abs/2504.03640 · HTML: https://mlsanity.com/paper/2504.03640/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 74 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 30 of 62)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [Large language model validity via enhanced conformal prediction methods](https://mlsanity.com/paper/2406.09714/) (2024)
- [X-FACT: A New Benchmark Dataset for Multilingual Fact Checking](https://mlsanity.com/paper/2106.09248/) (2021)
- [Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks](https://mlsanity.com/paper/2304.14732/) (2023)

## Built on by (most cited first, 1 of 1)

- [Always Tell Me The Odds: Fine-grained Conditional Probability Estimation](https://mlsanity.com/paper/2505.01595/) (2025)

## Abstract (arXiv)

To develop general-purpose collaborative agents, humans need reliable AI systems that can (1) adapt to new domains and (2) transparently reason with uncertainty to allow for verification and correction. Black-box models demonstrate powerful data processing abilities but do not satisfy these criteria due to their opaqueness, domain specificity, and lack of uncertainty awareness. We introduce Bonsai, a compositional and probabilistic reasoning system that generates adaptable inference trees by retrieving relevant grounding evidence and using it to compute likelihoods of sub-claims derived from broader natural language inferences. Bonsai's reasoning power is tunable at test-time via evidence scaling and it demonstrates reliable handling of varied domains including transcripts, photographs, videos, audio, and databases. Question-answering and human alignment experiments demonstrate that Bonsai matches the performance of domain-specific black-box methods while generating interpretable, grounded, and uncertainty-aware reasoning traces.