Challenge: Multi-label classification is prevalent in real-world settings, but the behavior of Large Language Models (LLMs) in this setting is understudied.
Approach: They propose to use initial probability distributions to analyze output distributions of LLMs at each label generation step to find out how LLM models perform multi-label classification.
Outcome: The proposed methods improve alignment and predictive performance over existing methods.

Similar Papers

Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale? (2025.coling-industry)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated great potential in complex tasks such as multi-label classification, but the vast number of labels can exceed LLMs’ input limits.
Approach: They propose a method that integrates large language models with dense retrieval techniques to overcome these challenges.
Outcome: The proposed methods avoid frequent retraining by leveraging zero-shot and few-shot learning for real-time label assignment.
Generalized Entropy Regularization or: There’s Nothing Special about Label Smoothing (2020.acl-main)

Copied to clipboard

Challenge: Prior work has explored regularizing the output distributions of probabilistic models to alleviate overfitting.
Approach: They propose a family of entropy regularizers that have a connection to regularization . they find that label smoothing provably does not allow for sparsity in an output distribution .
Outcome: The proposed method improves the relationship between model entropy and performance on language generation tasks.
Aligning Large Language Models for Controllable Recommendations (2024.acl-long)

Copied to clipboard

Challenge: Existing literature focuses on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template.
Approach: They propose a collection of supervised learning tasks augmented with labels derived from a conventional recommender model to improve LLMs’ proficiency in adhering to recommendation-specific instructions.
Outcome: The proposed approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.
Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) offer new opportunities to enhance the annotation process, particularly for detecting label errors in existing datasets.
Approach: They propose to use an ensemble of large language models to flag mislabeled examples by using an LLM-as-a-judge approach to detect label errors in existing datasets.
Outcome: The proposed method improves label accuracy and consistency in large language models.
Enhancing Language Model Alignment: A Confidence-Based Approach to Label Smoothing (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have remarkable capabilities across various domains . Reinforcement Learning with Human Feedback (RLHF) phase is crucial for training . label smoothing is a technique that replaces hard labels with soft labels .
Approach: They propose a method that iteratively updates the label smoothing parameter based on preference labels and model forecasts.
Outcome: The proposed method improves the performance of large language models on state-of-the-art alignment tasks.
Investigating Active Learning Sampling Strategies for Extreme Multi Label Text Classification (2022.lrec-1)

Copied to clipboard

Challenge: Large scale, multi-label text datasets with high numbers of different classes are expensive to annotate due to domain experts taking a lot of time working through all the classes.
Approach: They propose to build classifiers on multi-label text datasets using Active Learning to reduce labeling effort.
Outcome: The proposed classifiers can be used to reduce labeling effort on multi-label datasets.
LLMaAA: Making Large Language Models as Active Annotators (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing supervised learning methods in natural language processing require large amounts of data.
Approach: They propose an active learning loop that takes LLMs as annotators and puts them into an active loop to determine what to annotate efficiently.
Outcome: The proposed model outperforms existing models with few-shot performance in two NLP tasks.
Random Label Forests: An Ensemble Method with Label Subsampling For Extreme Multi-Label Problems (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for multi-label learning require large memory space for text classification . recent studies show that multiple labels are needed for e-commerce applications .
Approach: They propose a distributed ensemble method with label subsampling to share large memory space for handling large-scale labels.
Outcome: The proposed method can reduce memory usage while keeping competitive performance over real-world data sets.
SGM: Sequence Generation Model for Multi-label Classification (C18-1)

Copied to clipboard

Challenge: Existing methods ignore the correlations between labels and different parts of the text can contribute differently for predicting different labels.
Approach: They propose to view the multi-label classification task as a sequence generation problem and apply a decoder-based sequence generation model to solve it.
Outcome: The proposed methods outperform previous work by a substantial margin.
Beyond Performance: Quantifying and Mitigating Label Bias in LLMs (2024.naacl-long)

Copied to clipboard

Challenge: Large language models exhibit undesirable preference toward predicting certain answers over others, despite their adaptability to diverse tasks.
Approach: They propose a label bias calibration method that outperforms recent calibration approaches for improving performance and mitigating label bias.
Outcome: The proposed method outperforms calibration approaches for improving performance and mitigating label bias.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations