Interpretable NLP

https://arxiv.org/abs/2406.02981 Local vs. Global Interpretability: A Computational Complexity Perspective Shahaf Bassan, Guy Amir, Guy Katz The local and global interpretability of various ML models has been studied extensively in recent years. However, despite significant progress in the field, many known results remain informal or lack sufficient mathematical rigor. We propose a framework for bridging this gap, by using computational complexity theory to assess local and global perspectives of interpreting ML models. We begin by proposing proofs for two novel insights that are essential for our analysis: (1) a duality between local and global forms of explanations; and (2) the inherent uniqueness of certain global explanation forms. We then use these insights to evaluate the complexity of computing explanations, across three model types representing the extremes of the interpretability spectrum: (1) linear models; (2) decision trees; and (3) neural networks. Our findings offer insights into both the local and global interpretability of these models. For instance, under standard complexity assumptions such as P != NP, we prove that selecting global sufficient subsets in linear models is computationally harder than selecting local subsets. Interestingly, with neural networks and decision trees, the opposite is true: it is harder to carry out this task locally than globally. We believe that our findings demonstrate how examining explainability through a computational complexity lens can help us develop a more rigorous grasp of the inherent interpretability of ML models.

https://arxiv.org/abs/2404.13645 PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure Feiqi Cao, Caren Han, Hyunsuk Chung In this work, we propose a novel tree-based explanation technique, PEACH (Pretrained-embedding Explanation Across Contextual and Hierarchical Structure), that can explain how text-based documents are classified by using any pretrained contextual embeddings in a tree-based human-interpretable manner. Note that PEACH can adopt any contextual embeddings of the PLMs as a training input for the decision tree. Using the proposed PEACH, we perform a comprehensive analysis of several contextual embeddings on nine different NLP text classification benchmarks. This analysis demonstrates the flexibility of the model by applying several PLM contextual embeddings, its attribute selections, scaling, and clustering methods. Furthermore, we show the utility of explanations by visualising the feature selection and important trend of text classification via human-interpretable word-cloud-based trees, which clearly identify model mistakes and assist in dataset debugging. Besides interpretability, PEACH outperforms or is similar to those from pretrained models.

GitHub - aigents/iai: Interpretable Artificial Intelligence (IAI) Course Outline https://github.com/aigents/iai

Interpretable Recognition of Cognitive Distortions in Natural Language Texts Anton Kolonin, Anna Arinicheva We propose a new approach to multi-factor classification of natural language texts based on weighted structured patterns such as N-grams, taking into account the heterarchical relationships between them, applied to solve such a socially impactful problem as the automation of detection of specific cognitive distortions in psychological care, relying on an interpretable, robust and transparent artificial intelligence model. The proposed recognition and learning algorithms improve the current state of the art in this field. The improvement is tested on two publicly available datasets, with significant improvements over literature-known F1 scores for the task, with optimal hyper-parameters determined, having code and models available for future use by the community. https://arxiv.org/abs/2511.05969

https://agi-conference.org/ We are planning to have another workshop on Interpretable Natural Language Processing on the fields of the AGI-26 conference. Welcome your submissions here or in private!

The next A* NLP conference open for submission will be EMNLP-2025 https://2026.emnlp.org/ Submission deadline is May 25, 2026

Our new paper is published in PeerJ (Q1): https://peerj.com/articles/cs-3699/ Interpretable learning for detection of cognitive distortions from natural language texts Anton Germanovich Kolonin​​, Anna Andreevna Arinicheva​ We developed a technology that, based on a dataset annotated for cognitive distortions, builds an interpretable model capable of detecting cognitive distortions in natural language texts. The novelty of the approach lies in the fact that the learning and detection methods are based on structural patterns such as N-grams, incorporating heterarchical relationships between them through the “priority on order” principle. We investigated and released two types of detection models: plain binary classification and a model based on a multi-class representation. We optimized the hyperparameters of the models and achieved an accuracy of 0.92 and an F1-score of 0.95 in a cross-validation experiment. Additionally, we achieved over 1,000 times higher processing speed and lower computational cost compared to Large Language Model (LLM)-based alternatives.

https://agi-conference.org/call-for-papers We have applied for the 6th International Workshop on Interpretable Language Processing (INLP) to be held on the fields of Artificial General Intelligence (AGI) Conference series. While general conversational intelligence (GCI) can be considered one of the core aspects of AGI, the fields of AGI and NLP currently have little overlap, with few existing AGI architectures capable of comprehending natural language and nearly all NLP systems founded upon specialized, hardcoded rules and language-specific frameworks. This initiative is centered around the idea of INLP, an extension of the interpretable AI (IAI) concept to NLP; INLP allows for acquisition of natural language, comprehension of textual communications, and production of textual messages in a reasonable and transparent way. The proposed projects regarding Link Grammar (LG), unsupervised LG learning, interpretable NLG/NLS, ontologies, knowledge graphs and sentiment mining/topic matching cover various INLP methods that may bring a greater degree of GCI to proto-AGI pipelines.

🤚The Interpretable Natural Language Processing (INLP) workshop is scheduled for July 27th 9:00-12:00 Pacific Time (PDT) in the Annex 1 Hall at San Francisco State University (the exact workshop room is to be confirmed). For physical (non-free) and online (free) participation, register for AGI-2026 conference at https://luma.com/AGI-26 🗣Speakers: 1. Tatiana Shavrina, Meta, "Linguistic Grammar-based Scalable Machine Translation Approach for Underresourced Languages" 2. Sergey Shumsky, Symbolic Mind Inc. "Deep Control: An Interpretable Architecture for Hierarchical Language and Structural Reasoning" 3. Pavel Salowski, Partenit.io, "Automatic ontology creation using LLM" 4. Usman Gidago, Novosibirsk State University, "Interpretable Emotion Attribution in Social Graphs: A comparative Analysis of Rule-based, Transformer, and LLM models" 5. Anna Arinicheva, Assistant of Psychologist, "Interpretable Recognition of Cognitive Distortions in Natural Language Texts" For speakers and registered virtual participants, Zoom links will be provided. 🖐Please register! https://luma.com/AGI-26

Interesting study and dataset: Temporal Explanation Benchmark Suite https://github.com/IvanReznikov/Natural-Language-Explainability-for-Temporal-KGs/tree/main https://github.com/IvanReznikov/Natural-Language-Explainability-for-Temporal-KGs/blob/main/docs/RESULTS_M3.md

Starting in 14 minutes https://www.youtube.com/live/mXabs2OnWU0

🗣The Interpretable Natural Language Processing (INLP) workshop July 27th, 2026, on the fields of AGI-26 Conference Speakers: 1. Tatiana Shavrina, Meta, "Linguistic Grammar-based Scalable Machine Translation Approach for Underresourced Languages" 2. Sergey Shumsky, Symbolic Mind Inc. "Deep Control: An Interpretable Architecture for Hierarchical Language and Structural Reasoning" 3. Pavel Salowski, Partenit.io, "Automatic ontology creation using LLM" 4. Usman Gidago, Novosibirsk State University, "Interpretable Emotion Attribution in Social Graphs: A comparative Analysis of Rule-based, Transformer, and LLM models" 5. Anna Arinicheva, Assistant of Psychologist, "Interpretable Recognition of Cognitive Distortions in Natural Language Texts" https://www.youtube.com/live/mXabs2OnWU0