llmSHAP 1.0.1

Multi-threaded Shapley explainability for LLMs: words, sentences, documents, and tools.

llmSHAP

A multi-threaded explainability framework using Shapley values for LLM-based outputs.

---

Getting started

Install the llmshap package (with all optional dependencies):

pip install "llmshap[full]"

Install in editable mode with all optional dependencies (after cloning the repository):

pip install -e ".[full]"

Documentation is available at llmSHAP Docs and a hands-on tutorial can be found here.

• Full documentation
• Tutorial

---

Example usage

from llmSHAP import DataHandler, BasicPromptCodec, ShapleyAttribution
from llmSHAP.llm import OpenAIInterface

data = "In what city is the Eiffel Tower?"
handler = DataHandler(data, permanent_keys={0,3,4})
prompt_codec = BasicPromptCodec(system="Answer the question briefly.")
llm = OpenAIInterface("gpt-4o-mini")

shap = ShapleyAttribution(model=llm,
                          data_handler=handler,
                          prompt_codec=prompt_codec,
                          use_cache=True,
                          num_threads=7)
result = shap.attribution()

print("\n\n### OUTPUT ###")
print(result.output)

print("\n\n### ATTRIBUTION ###")
print(result.attribution)

print("\n\n### HEATMAP ###")
print(result.render())

---

Example data

You can pass either a string or a dictionary:

from llmSHAP import DataHandler

# String input
data = "The quick brown fox jumps over the lazy dog"
handler = DataHandler(data)

# Dictionary input
data = {"a": "The", "b": "quick", "c": "brown", "d": "fox"}
handler = DataHandler(data)

To exclude certain keys from the computations, use permanent_keys:

from llmSHAP import DataHandler

data = {"a": "The", "b": "quick", "c": "brown", "d": "fox"}
handler = DataHandler(data, permanent_keys={"a", "d"})

# Get data with index 1 WITHOUT the permanent features.
print(handler.get_data({1}, exclude_permanent_keys=True, mask=False))
# Output: {'b': 'quick'}

# Get data with index 1 AND the permanent features.
print(handler.get_data({1}, exclude_permanent_keys=False, mask=False))
# Output: {'a': 'The', 'b': 'quick', 'd': 'fox'}

---

Comparison with TokenSHAP

Capability	llmSHAP	TokenSHAP
Threaded	✅ (optional num_threads)	❌
Modular architecture	✅	❌
Exact Shapley option	✅ (Full enumeration)	❌ (Monte Carlo sampling)
Generation caching across coalitions	✅	❌
Heuristics	SlidingWindow • Monte Carlo • Counterfactual	Monte Carlo
Sentence-/chunk-level attribution	✅	✅
Permanent context pinning (always-included features)	✅	❌
Pluggable similarity metric	✅ TF-IDF, embeddings	✅ TF-IDF, embeddings
Docs & tutorial	✅ Sphinx docs + tutorial	✅ README only
Unit tests & CI	✅ Pytest + GitHub Actions	❌
Vision object attribution	❌	✅ PixelSHAP