Self-Regularization with Latent Space Explanations for Controllable LLM-based Classification

• URL: http://arxiv.org/abs/2502.14133v1
• Date: Wed, 19 Feb 2025 22:27:59 GMT
• Title: Self-Regularization with Latent Space Explanations for Controllable LLM-based Classification
• Authors: Xuansheng Wu, Wenhao Yu, Xiaoming Zhai, Ninghao Liu,
• Abstract summary: We propose a novel framework to identify and regularize unintended features in large language models (LLMs) latent spaces. We evaluate the proposed framework on three real-world tasks, including toxic chat detection, reward modeling, and disease diagnosis.
• Score: 29.74457390987092
• License:
• Abstract: Modern text classification methods heavily rely on contextual embeddings from large language models (LLMs). Compared to human-engineered features, these embeddings provide automatic and effective representations for classification model training. However, they also introduce a challenge: we lose the ability to manually remove unintended features, such as sensitive or task-irrelevant features, to guarantee regulatory compliance or improve the generalizability of classification models. This limitation arises because LLM embeddings are opaque and difficult to interpret. In this paper, we propose a novel framework to identify and regularize unintended features in the LLM latent space. Specifically, we first pre-train a sparse autoencoder (SAE) to extract interpretable features from LLM latent spaces. To ensure the SAE can capture task-specific features, we further fine-tune it on task-specific datasets. In training the classification model, we propose a simple and effective regularizer, by minimizing the similarity between the classifier weights and the identified unintended feature, to remove the impacts of these unintended features toward classification. We evaluate the proposed framework on three real-world tasks, including toxic chat detection, reward modeling, and disease diagnosis. Results show that the proposed framework can significantly improve the classifier's generalizability by regularizing those features that are not semantically correlated to each task. This work pioneers controllable text classification on LLM latent spaces by leveraging interpreted features to address generalizability, fairness, and privacy challenges. We will release our code and data once accepted.

Related papers

• Disentangling CLIP Features for Enhanced Localized Understanding [58.73850193789384]
  We propose Unmix-CLIP, a novel framework designed to reduce mutual feature information (MFI) and improve feature disentanglement. For the COCO- 14 dataset, Unmix-CLIP reduces feature similarity by 24.9%.
  arXiv  Detail & Related papers  (2025-02-05T08:20:31Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• LLM-based feature generation from text for interpretable machine learning [0.0]
  Existing text representations such as embeddings and bag-of-words are not suitable for rule learning due to their high dimensionality and absent or questionable feature-level interpretability. This article explores whether large language models (LLMs) could address this by extracting a small number of interpretable features from text.
  arXiv  Detail & Related papers  (2024-09-11T09:29:28Z)
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations [29.32704733570445]
  We introduce Llama Guard, an input-output safeguard model geared towards Human-AI conversation use cases. Llama Guard incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks. Llama Guard demonstrates strong performance on existing benchmarks such as the OpenAI Moderation Evaluation dataset and ToxicChat.
  arXiv  Detail & Related papers  (2023-12-07T19:40:50Z)
• Token Prediction as Implicit Classification to Identify LLM-Generated Text [37.89852204279844]
  This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a next-token prediction task. We utilize the Text-to-Text Transfer Transformer (T5) model as the backbone for our experiments.
  arXiv  Detail & Related papers  (2023-11-15T06:33:52Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems [61.11799513362704]
  We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
  arXiv  Detail & Related papers  (2023-03-03T02:07:40Z)
• Task-Specific Embeddings for Ante-Hoc Explainable Text Classification [6.671252951387647]
  We propose an alternative training objective in which we learn task-specific embeddings of text. Our proposed objective learns embeddings such that all texts that share the same target class label should be close together. We present extensive experiments which show that the benefits of ante-hoc explainability and incremental learning come at no cost in overall classification accuracy.
  arXiv  Detail & Related papers  (2022-11-30T19:56:25Z)
• Bias-Eliminated Semantic Refinement for Any-Shot Learning [27.374052527155623]
  We refine the coarse-grained semantic description for any-shot learning tasks. A new model, namely, the semantic refinement Wasserstein generative adversarial network (SRWGAN) model, is designed. We extensively evaluate model performance on six benchmark datasets.
  arXiv  Detail & Related papers  (2022-02-10T04:15:50Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption [72.35532598131176]
  We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features. We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
  arXiv  Detail & Related papers  (2021-06-29T08:08:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.