# Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models

arXiv: https://arxiv.org/abs/2406.07001 · HTML: https://mlsanity.com/paper/2406.07001/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [Benchmarking Natural Language Understanding Services for building Conversational Agents](https://mlsanity.com/paper/1903.05566/) (2019)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023)
- [BertGCN: Transductive Text Classification by Combining GCN and BERT](https://mlsanity.com/paper/2105.05727/) (2021)
- [Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought](https://mlsanity.com/paper/2308.08614/) (2023)
- [In-Context Learning for Text Classification with Many Labels](https://mlsanity.com/paper/2309.10954/) (2023)
- [Description Based Text Classification with Reinforcement Learning](https://mlsanity.com/paper/2002.03067/) (2020)
- [ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification](https://mlsanity.com/paper/2305.09269/) (2023)
- [Effective Structured Prompting by Meta-Learning and Representative Verbalizer](https://mlsanity.com/paper/2306.00618/) (2023)
- [Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection](https://mlsanity.com/paper/2304.01238/) (2023)
- [InstanT: Semi-supervised Learning with Instance-dependent Thresholds](https://mlsanity.com/paper/2310.18910/) (2023)
- [Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance](https://mlsanity.com/paper/2308.14634/) (2023)
- [Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification](https://mlsanity.com/paper/2305.14827/) (2023)
- [BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions](https://mlsanity.com/paper/2310.06111/) (2023)
- [Boosting Few-Shot Text Classification via Distribution Estimation](https://mlsanity.com/paper/2303.16764/) (2023)
- [TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation](https://mlsanity.com/paper/2306.02175/) (2023)

## Built on by (most cited first, 9 of 9)

- [Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging](https://mlsanity.com/paper/2406.15479/) (2024)
- [CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning](https://mlsanity.com/paper/2410.10336/) (2024)
- [On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion](https://mlsanity.com/paper/2406.15480/) (2024)
- [Demonstration Selection for In-Context Learning via Reinforcement Learning](https://mlsanity.com/paper/2412.03966/) (2024)
- [Mitigating Multilingual Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2408.00550/) (2024)
- [Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models](https://mlsanity.com/paper/2512.21964/) (2025)
- [Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement](https://mlsanity.com/paper/2510.01910/) (2025)
- [MIN-Merging: Merge the Important Neurons for Model Merging](https://mlsanity.com/paper/2510.17890/) (2025)
- [Entropy-Based Data Selection for Language Models](https://mlsanity.com/paper/2602.17465/) (2026)

## Abstract (arXiv)

Text classification is a crucial task encountered frequently in practical scenarios, yet it is still under-explored in the era of large language models (LLMs). This study shows that LLMs are vulnerable to changes in the number and arrangement of options in text classification. Our extensive empirical analyses reveal that the key bottleneck arises from ambiguous decision boundaries and inherent biases towards specific tokens and positions. To mitigate these issues, we make the first attempt and propose a novel two-stage classification framework for LLMs. Our approach is grounded in the empirical observation that pairwise comparisons can effectively alleviate boundary ambiguity and inherent bias. Specifically, we begin with a self-reduction technique to efficiently narrow down numerous options, which contributes to reduced decision space and a faster comparison process. Subsequently, pairwise contrastive comparisons are employed in a chain-of-thought manner to draw out nuances and distinguish confusable options, thus refining the ambiguous decision boundary. Extensive experiments on four datasets (Banking77, HWU64, LIU54, and Clinic150) verify the effectiveness of our framework. Furthermore, benefitting from our framework, various LLMs can achieve consistent improvements. Our code and data are available in urlhttps://github.com/Chuge0335/PC-CoT.