# LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text

arXiv: https://arxiv.org/abs/2601.11746 · HTML: https://mlsanity.com/paper/2601.11746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation](https://mlsanity.com/paper/1802.00682/) (2018)
- [DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems](https://mlsanity.com/paper/1906.10263/) (2019)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2012.03058/) (2020)
- [OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms](https://mlsanity.com/paper/2006.05714/) (2020)
- [GLIME: General, Stable and Local LIME Explanation](https://mlsanity.com/paper/2311.15722/) (2023)
- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach](https://mlsanity.com/paper/2402.03043/) (2024)
- [Explaining text classifiers through progressive neighborhood approximation with realistic samples](https://mlsanity.com/paper/2302.07733/) (2023)
- [Transparent Neighborhood Approximation for Text Classifier Explanation](https://mlsanity.com/paper/2411.16251/) (2024)

## Abstract (arXiv)

Local explanation methods such as LIME (Ribeiro et al., 2016) remain fundamental to trustworthy AI, yet their application to NLP is limited by a reliance on random token masking. These heuristic perturbations frequently generate semantically invalid, out-of-distribution inputs that weaken the fidelity of local surrogate models. While recent generative approaches such as LLiMe (Angiulli et al., 2025b) attempt to mitigate this by employing Large Language Models for neighborhood generation, they rely on unconstrained paraphrasing that introduces confounding variables, making it difficult to isolate specific feature contributions. We introduce LIME-LLM, a framework that replaces random noise with hypothesis-driven, controlled perturbations. By enforcing a strict "Single Mask-Single Sample" protocol and employing distinct neutral infill and boundary infill strategies, LIME-LLM constructs fluent, on-manifold neighborhoods that rigorously isolate feature effects. We evaluate our method against established baselines (LIME, SHAP, Integrated Gradients) and the generative LLiMe baseline across three diverse benchmarks: CoLA, SST-2, and HateXplain using human-annotated rationales as ground truth. Empirical results demonstrate that LIME-LLM establishes a new benchmark for black-box NLP explainability, achieving significant improvements in local explanation fidelity compared to both traditional perturbation-based methods and recent generative alternatives.