Augmenting Interpretable Models with LLMs during Training
Abstract
Domain fit: AI-core · Core AI workload signals detected from paper context and implementation/artifact evidence.
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their proliferation into high-stakes domains (e.g. medicine) and compute-limited settings has created a burgeoning need for interpretability and efficiency. We address this need by proposing Augmented Interpretable Models (Aug-imodels), a framework for leveraging the knowledge learned by LLMs to build extremely efficient and interpretable models. Aug-imodels use LLMs during fitting but not during inference, allowing complete transparency and often a speed/memory improvement of greater than 1,000x for inference compared to LLMs. We explore two instantiations of Aug-imodels in natural-language processing: (i) Aug-GAM, which augments a generalized additive model with decoupled embeddings from an LLM and (ii) Aug-Tree, which augments a decision tree with LLM feature expansions. Across a variety of text-classification datasets, both outperform their non-augmented counterparts. Aug-GAM can even outperform much larger models (e.g. a 6-billion parameter GPT-J model), despite having 10,000x fewer parameters and being fully transparent. We further explore Aug-imodels in a natural-language fMRI study, where they generate interesting interpretations from scientific data. All code for using Aug-imodels and reproducing results is made available on Github.
Results and benchmarks
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks.
Benchmark evidence is limited
Evidence graph: 2 refs, 1 links.
Utility signals: depth 65/100, grounding 58/100, status medium.
Implementation
No direct implementation yet
Maintained implementation evidence is not confirmed for this paper yet.
Use the implementation status and reproduction sections for the current action plan.
No verified maintained repo yet
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No direct maintained implementation was found. Use the paper PDF and citation graph to design a baseline reproduction.
- Start from related paper: Measuring Interpretability for Different Types of Machine Learning Models.
- Track assumptions and missing details in an experiment log before coding.
Time to first repro: a few days
Recommendation evidence is currently too limited for a maintained-repo choice. Use Implementation Status and Reproduction Path for a practical baseline plan.
- Estimate is based on paper-only reproduction flow
Reproduction readiness
No repo
No verified implementation available
- No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
Hardware requirements
- Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Validation caveat
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet. Use targeted searches to quickly locate candidate models, datasets, and demos.
Datasets
Spaces
Tip: start with models, then check datasets and spaces if you need evaluation data or demos.
Research context
1
Citations
74
References
Tasks
Interpretability, Inference, Computer science, Variety (cybernetics), Code (set theory), Transparency (behavior), Decision tree, Tree (set theory)
Methods
Transformer
Domains
Artificial intelligence, Machine learning, Natural language processing
Related papers
- Measuring Interpretability for Different Types of Machine Learning ModelsSearch on Paper2Code
2018 · Semantic similarity
- Measures of Model Interpretability for Model SelectionSearch on Paper2Code
2018 · Semantic similarity
- ML Interpretability: Simple Isn't EasySearch on Paper2Code
2022 · Semantic similarity
- When consumers need more interpretability of artificial intelligence (AI) recommendations? The effect of decision-making domainsSearch on Paper2Code
2023 · Semantic similarity
- ML interpretability: Simple isn't easySearch on Paper2Code
2024 · Semantic similarity
- Analyzing Effects of Mixed Sample Data Augmentation on Model InterpretabilitySearch on Paper2Code
2023 · Semantic similarity
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXJump to Paper2Code search queries derived from this paper's research context.