Pith. sign in

REVIEW 9 cited by

A Survey of the State of Explainable AI for Natural Language Processing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.00711 v1 pith:XJJFXWNR submitted 2020-10-01 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords explanationscurrentexplainableimportantlanguagemodelmodelsnatural
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 113 citations worldwide. Full citation record

  1. Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks

    cs.LG 2026-02 conditional novelty 6.0 of 10

    A structured dual-target attack can force targeted misclassification of time series while keeping the explainer aligned with a reference rationale, showing explanation stability is not a reliable robustness proxy.

  2. KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations

    cs.LG 2025-07 reject novelty 6.0 of 10

    KGRAG-Ex retrieves answer-relevant paths through a knowledge graph, turns them into natural-language paragraphs, and explains each answer by removing individual graph nodes, edges, or sub-paths and observing whether t...

  3. Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study

    cs.AI 2025-08 reject novelty 4.0 of 10

    An LLM-agent layer wraps a standard inventory transshipment MIP to produce role-aware, explainable supply chain plans, demonstrated on a constructed five-DC stockout scenario.

  4. LUST: A Multi-Modal Framework with Hierarchical LLM-based Scoring for Learned Thematic Significance Tracking in Multimedia Content

    cs.MM 2025-08 reject novelty 4.0 of 10

    LUST is an unevaluated video analysis framework that combines ASR transcripts and frames with hierarchical LLM prompts to score segment relevance to a user theme.

  5. Pareto Optimal Algorithmic Recourse in Multi-cost Function

    cs.LG 2025-02 reject novelty 4.0 of 10

    A Bellman-Ford-style dynamic program over an actionability graph returns all Pareto-optimal recourse paths for multiple non-differentiable metric costs, with an epsilon-net sampling scheme proposed for scalability.

  6. The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition

    cs.AI 2025-01 conditional novelty 4.0 of 10

    Words that strongly activate both a lower-layer neuron and its strongly connected upper-layer neuron in GPT-2XL form more semantically similar clusters, which the paper interprets as a clipping process.

  7. Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces

    cs.CL 2025-04 reject novelty 3.0 of 10

    A GPT2-XL analysis reports that a neuron's highest-activation tokens are also the ones most similar to multiple categorical subclusters, offered as evidence for an intra-neuronal vector-space view of polysemy.

  8. How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons

    q-bio.NC 2024-12 reject novelty 2.0 of 10

    The paper names three components of a neuron's aggregation function as cognitive factors and reports near-unity correlations in GPT-2XL, but the effects are largely true by construction.

  9. A Comprehensive Guide to Explainable AI: From Classical Models to LLMs

    cs.LG 2024-12 unverdicted novelty 1.0 of 10

    A survey-style XAI book with code examples, covering standard interpretability methods and models, but no new scientific contributions.

Pith tools