ACL Findings2024
SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification
Difan Jiao, Yilun Liu, Zhenwei Tang, Daniel Matter, Jürgen Pfeffer, Ashton Anderson
Abstract
Among the many tasks that Large Language Models (LLMs) have revolutionized is text classification. Current text classification paradigms, however, rely solely on the output of the final layer in the LLM, with the rich information contained in internal neurons largely untapped. In this study, we present SPIN 1 : a model-agnostic framework that sparsifies and integrates internal neurons of intermediate layers of LLMs for text classification. Specifically, SPIN sparsifies internal neurons by linear probing-based salient neuron selection layer by layer, avoiding noise from unrelated neurons and ensuring efficiency. The cross-layer salient neurons are then integrated to serve as multi-layered features for the classification head. Extensive experimental results show that our proposed framework can significantly improve text classification accuracy, efficiency, and interpretability.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- LoRA: Low-Rank Adaptation of Large Language Models cites Language Models are Few-Shot Learners
- Robustness of Mixtures of Experts to Feature Noise cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Towards a Unified View of Parameter-Efficient Transfer Learning cites Language Models are Few-Shot Learners
Cited by top-tier papers4
- LLM Safety From Within: Detecting Harmful Content with Internal RepresentationsDifan Jiao, Yilun Liu, Ye Yuan, Zhenwei Tang et al.ACL 2026 · 3 citations
- Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable PersonalizationWeixu Zhang, Ye Yuan, Changjiang Han, Yuxing Tian et al.ACL 2026 · 2 citations
- Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMsZhuoxuan Zhang, Jinhao Duan, Edward Kim, Kaidi XuEMNLP 2025 · 1 citation
- Robustness of Mixtures of Experts to Feature NoiseDong Sun, Rahul Nittala, Rebekka BurkholzICML 2026 · 1 citation
Builds on13
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Towards a Unified View of Parameter-Efficient Transfer LearningJunxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick et al.ICLR 2022 · 1,182 citations
Related papers
- Self-Regularization with Sparse Autoencoders for Controllable LLM-based ClassificationXuansheng Wu, Wenhao Yu, Xiaoming Zhai, Ninghao LiuKDD 2025
- Wasserstein Distances, Neuronal Entanglement, and SparsityShashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh et al.ICLR 2025
- Finding and Editing Multi-Modal Neurons in Pre-Trained TransformersHaowen Pan, Yixin Cao, Xiaozhi Wang, Xun Yang et al.ACL Findings 2024 · 8 citations
- Discovering Decoupled Functional Modules in Large Language ModelsYanke Yu, Jin Li, Ying Sun, Ping Li et al.AAAI 2026
- Concept Bottleneck Large Language ModelsChung-En Sun, Tuomas P. Oikarinen, Berk Ustun, Tsui-Wei WengICLR 2025
