Papers › Variational Language Concepts for Interpreting Foundation Language Models

Variational Language Concepts for Interpreting Foundation Language Models

4 Oct 2024arXiv:2410.03964archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections