No article text was recorded for this version.
gradient-based feature attribution
Version 2 of 2291 papers309 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Opening the Black Box: Unraveling the Classroom Dialogue Analysis (Student Abstract)
- Blog: Painsight: An Extendable Opinion Mining Framework for Detecting Pain Points Based on Online Customer Reviews
- Blog: Painsight: An Extendable Opinion Mining Framework for Detecting Pain Points Based on Online Customer Reviews
- Blog: Automatic Text Scoring Using Neural Networks
- Blog: Unveiling and Manipulating Prompt Influence in Large Language Models
- Blog: Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation
- Blog: Detecting, Explaining, and Mitigating Memorization in Diffusion Models
- Blog: First is Better Than Last for Language Data Influence
- Blog: Defending against Insertion-based Textual Backdoor Attacks via Attribution
- Blog: Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
- Blog: Token-wise Influential Training Data Retrieval for Large Language Models
- Blog: Text Revision by On-the-Fly Representation Optimization
- Blog: Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
- Blog: Do Multi-Lingual Pre-trained Language Models Reveal Consistent Token Attributions in Different Languages?
- Blog: Do Multi-Lingual Pre-trained Language Models Reveal Consistent Token Attributions in Different Languages?
- Blog: Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
- Blog: AdapLeR: Speeding up Inference by Adaptive Length Reduction
- Blog: Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence
- Blog: Extraction of Salient Sentences from Labelled Documents
- Blog: Automatic Text Scoring Using Neural Networks
- Blog: Explaining Translationese: why are Neural Classifiers Better and what do they Learn?
- Blog: Detecting, Explaining, and Mitigating Memorization in Diffusion Models
- Blog: Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution
- Blog: Interpreting BERT-based Text Similarity via Activation and Saliency Maps
- Blog: Distributed Rule Vectors is A Key Mechanism in Large Language Models' In-Context Learning
- Blog: Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools
- Blog: Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
- Blog: Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
- Blog: How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
- Blog: Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations
- Blog: Understanding the Dark Side of LLMs' Intrinsic Self-Correction
- Blog: Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
- Blog: Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
- Blog: When AI explains in natural language: Unveiling the impact of generative AI explanations on educators’ grading and feedback practices
- Blog: Human-grounded Evaluations of Explanation Methods for Text Classification
- Blog: Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps
- Blog: Latent Concept-based Explanation of NLP Models
- Blog: SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation
- Blog: Towards Crafting Text Adversarial Samples
- Blog: Toxicity in Multilingual Machine Translation at Scale
- Blog: Saliency-driven Word Alignment Interpretation for Neural Machine Translation
- Blog: Revisiting subword tokenization: A case study on affixal negation in large language models
- Blog: Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
- Blog: GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models
- Blog: On Measuring Context Utilization in Document-Level MT Systems
- Blog: Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
- Blog: Visualizing and Understanding Neural Models in NLP
- Blog: The Overlooked Repetitive Lengthening Form in Sentiment Analysis
- Blog: Large Language Models Understand and Can be Enhanced by Emotional Stimuli
- Blog: Multi-task Learning for Paraphrase Generation With Keyword and Part-of-Speech Reconstruction
- Blog: Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
- Blog: Measuring Fairness of Text Classifiers via Prediction Sensitivity
- Blog: Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
- Blog: Exploring Distantly-Labeled Rationales in Neural Network Models
- Blog: A Diachronic Analysis of Human and Model Predictions on Audience Gender in How-to Guides
- Blog: Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
- Blog: Investigating Mysteries of CoT-Augmented Distillation
- Blog: The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
- Blog: Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation
- Blog: Mitigating Text Toxicity with Counterfactual Generation
Showing 60 of 291 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_based_feature_attribution_37fe3a98,
title = {gradient-based feature attribution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-based-feature-attribution/rdr_37fe3a98e9954fea98e1605025fd6633},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_gradient_based_feature_attribution_37fe3a98_v2,
title = {gradient-based feature attribution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-based-feature-attribution/rdr_37fe3a98e9954fea98e1605025fd6633/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}