# Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval

arXiv: https://arxiv.org/abs/2608.06614 · HTML: https://mlsanity.com/paper/2608.06614/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Understanding the Dark Side of LLMs' Intrinsic Self-Correction](https://mlsanity.com/paper/2412.14959/) (2024)
- [Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs](https://mlsanity.com/paper/2412.19513/) (2024)
- [LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL](https://mlsanity.com/paper/2503.18596/) (2025)
- [Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation](https://mlsanity.com/paper/2402.11827/) (2024)
- [ProgCo: Program Helps Self-Correction of Large Language Models](https://mlsanity.com/paper/2501.01264/) (2025)
- [Improving Table Retrieval with Question Generation from Partial Tables](https://mlsanity.com/paper/2508.06168/) (2025)
- [ICR: Iterative Clarification and Rewriting for Conversational Search](https://mlsanity.com/paper/2509.05100/) (2025)
- [Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning](https://mlsanity.com/paper/2601.07782/) (2026)
- [Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search](https://mlsanity.com/paper/2604.06771/) (2026)

## Abstract (arXiv)

Large-taxonomy retrieval often assumes that the input already expresses the target concept. In many settings, however, the input is indirect evidence, such as a table cell whose meaning depends on its row, column, datatype, and context. We call this mismatch the retrieval readiness gap. Our analysis shows that the current index retrieves the target reliably when its semantics are explicit, while raw evidence often leaves it deep in the ranking. We propose Factorized Hypothesis Search (FHS), which maintains multiple partial interpretations over named semantic dimensions. These hypotheses support structured query rendering, multi-hypothesis retrieval, and dimension-level candidate verification. On both financial taxonomy tagging and CodiEsp clinical coding tasks, FHS achieves the best Recall@1, MRR, and final accuracy among the non-oracle methods. Replacing the factorized hypothesis path with a free-text ensemble causes the largest drop in head-ranking performance, while sequential refinement provides no additional gain over FHS's strong parallel first round.