paper-with-me

Papers

Variational Language Concepts for Interpreting Foundation Language Models

2024-10-04 · Hengyi Wang, Shiwei Tan, Zhiqing Hong, Desheng Zhang, Hao Wang

Foundation Language Models (FLMs) such as BERT and its variants have achieved remarkable success in natural language processing. To date, the interpretability of FLMs has primarily relied on the attention weights in their self-attention layers. However, these attention weights only provide word-level interpretations, failing to capture higher-level structures, and are therefore lacking in readability and intuitiveness. To address this challenge, we first provide a formal definition of conceptual interpretation and then propose a variational Bayesian framework, dubbed VAriational Language Concept (VALC), to go beyond word-level interpretations and provide concept-level interpretations. Our theoretical analysis shows that our VALC finds the optimal language concepts to interpret FLM predictions. Empirical results on several real-world datasets show that our method can successfully provide conceptual interpretation for FLMs.

📄 PDF Abstract BibTeX arXiv:2410.03964

Code (1)

Wang-ML-Lab/interpretable-foundation-models 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

CFM: Language-aligned Concept Foundation Model for Vision

2026-01-20 · Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele 외 arxiv

Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-making difficult. Recent work decompose the…

Image Classification

Self-Supervised Intermediate Fine-Tuning of Biomedical Language Models for Interpreting Patient Case Descriptions

2022-10-01 · COLING 2022 10 · Israa Alghanmi, Luis Espinosa-Anke, Steven Schockaert

Interpreting patient case descriptions has emerged as a challenging problem for biomedical NLP, where the aim is typically to predict diagnoses, to recommended treatments, or to answer questions about cases more generall…

CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries

2025-01-02 · Shudong Liu, Yiqiao Jin, Cheng Li, Derek F. Wong 외

Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding, often misinterpreting symbols, gestures, and artifacts due to biases in predominantly Western-centric training da…

Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models

2025-10-29 · Charlotte Claye, Pierre Marschall, Wassila Ouerdane, Céline Hudelot 외 arxiv

Single-cell RNA-seq foundation models achieve strong performance on downstream tasks but remain black boxes, limiting their utility for biological discovery. Recent work has shown that sparse dictionary learning can extr…

From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models

2025-06-01 · Asım Ersoy, Basel Mousi, Shammur Chowdhury, Firoj Alam 외

The emergence of large language models (LLMs) has demonstrated that systems trained solely on text can acquire extensive world knowledge, develop reasoning capabilities, and internalize abstract semantic concepts--showca…

World Knowledge