# From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification

arXiv: https://arxiv.org/abs/2609.01564 · HTML: https://mlsanity.com/paper/2609.01564/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking](https://mlsanity.com/paper/2311.06102/) (2023)
- [Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale?](https://mlsanity.com/paper/2412.05137/) (2024)
- [Text Classification in the LLM Era -- Where do we stand?](https://mlsanity.com/paper/2502.11830/) (2025)

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

- [Label-Centric Knowledge Retrieval for Zero-Shot Text Classification](https://mlsanity.com/paper/2610.16182/) (2026)

## Abstract (arXiv)

Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large label spaces, a common approach retrieves top-K candidate labels by embedding similarity and prompt the LLM to choose among them. However, top-K retrieval reduces the number of candidates but does not help the model tell similar ones apart. When two similar labels both appear as candidates, the model lacks the signal to choose correctly between them. We propose a framework that (1) identifies which label pairs the model struggles to distinguish, (2) expands the candidate set to include confusable labels, and (3) generates targeted rules to differentiate between similar candidates. The framework requires no fine-tuning, and the generated rules transfer to smaller, cheaper models. On three benchmarks (WOS, Flipkart, LEDGAR), our approach improves Macro F1 by up to 10.0pp over retrieval baselines, with smaller models (2B--20B) gaining up to 11.5pp via cross-model transfer.