# Crafting Large Language Models for Enhanced Interpretability

arXiv: https://arxiv.org/abs/2407.04307 · HTML: https://mlsanity.com/paper/2407.04307/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models](https://mlsanity.com/paper/1812.09355/) (2018)
- [The emergence of number and syntax units in LSTM language models](https://mlsanity.com/paper/1903.07435/) (2019)
- [On the Pitfalls of Analyzing Individual Neurons in Language Models](https://mlsanity.com/paper/2110.07483/) (2021)
- [The Importance of Prompt Tuning for Automated Neuron Explanations](https://mlsanity.com/paper/2310.06200/) (2023)

## Built on by (most cited first, 8 of 8)

- [VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance](https://mlsanity.com/paper/2408.01432/) (2024)
- [ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models](https://mlsanity.com/paper/2503.22048/) (2025)
- [Concept Bottleneck Language Models For protein design](https://mlsanity.com/paper/2411.06090/) (2024)
- [Towards Achieving Concept Completeness for Textual Concept Bottleneck Models](https://mlsanity.com/paper/2502.11100/) (2025)
- [Interacting Large Language Model Agents. Interpretable Models and Social Learning](https://mlsanity.com/paper/2411.01271/) (2024)
- [Steer2Edit: From Activation Steering to Component-Level Editing](https://mlsanity.com/paper/2602.09870/) (2026)
- [The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation](https://mlsanity.com/paper/2608.22956/) (2026)
- [Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes](https://mlsanity.com/paper/2610.06889/) (2026)

## Abstract (arXiv)

We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with limited neuron function insights, CB-LLM sets a new standard with its built-in interpretability, scalability, and ability to provide clear, accurate explanations. This innovation not only advances transparency in language models but also enhances their effectiveness. Our unique Automatic Concept Correction (ACC) strategy successfully narrows the performance gap with conventional black-box LLMs, positioning CB-LLM as a model that combines the high accuracy of traditional LLMs with the added benefit of clear interpretability -- a feature markedly absent in existing LLMs.