Tagged articles

20 articles

Page 1 of 1

May 17, 2026 · Artificial Intelligence

Turning LLMs into CT Scans: How Alibaba’s Safe‑SAIL Makes AI Decision Black Boxes Transparent

The paper introduces Safe‑SAIL, a Sparse Autoencoder Interpretation Framework for LLMs that provides pre‑explanation metrics, a segment‑level simulation to cut evaluation cost, and a 1,758‑feature safety database, enabling transparent analysis and interactive debugging of large language model safety decisions.

InterpretabilityLLMSafety

0 likes · 12 min read

Turning LLMs into CT Scans: How Alibaba’s Safe‑SAIL Makes AI Decision Black Boxes Transparent

Old Zhang's AI Learning

May 3, 2026 · Artificial Intelligence

Alibaba’s Qwen‑Scope: A Brain‑Computer Interface for Qwen‑3.5‑27B

Qwen‑Scope adds a sparse autoencoder (SAE) to the Qwen‑3.5‑27B model, exposing a top‑K 50‑feature, residual‑stream hook across all 64 layers for interpretability, controllable generation, data analysis, and training diagnostics, while detailing installation, usage, and practical trade‑offs.

InterpretabilityQwenSAE

0 likes · 11 min read

Alibaba’s Qwen‑Scope: A Brain‑Computer Interface for Qwen‑3.5‑27B

Machine Heart

May 1, 2026 · Artificial Intelligence

LLMs Write and Evolve Code to Redefine Quantitative Factor Mining – The CogAlpha ACL Paper

The CogAlpha framework upgrades Alpha discovery from static formulas to executable Python code, organizes a 7‑layer, 21‑agent research hierarchy, iteratively evolves factor candidates, and on CSI300 10‑day prediction outperforms 21 baselines with a 16.39% annual excess return and an IR of 1.8999, demonstrating that large models can actively participate in the discovery process.

ACL 2026Alpha MiningCode Generation

0 likes · 9 min read

LLMs Write and Evolve Code to Redefine Quantitative Factor Mining – The CogAlpha ACL Paper

PaperAgent

Jan 22, 2026 · Artificial Intelligence

How STEM Replaces MoE Routing with Simple Table Lookup for Faster Transformers

The article presents STEM, a method that transforms dense and MoE transformer architectures by converting the expert routing step into a static table‑lookup operation, achieving higher parameter efficiency, lower communication overhead, and improved interpretability while maintaining or boosting downstream task performance.

Embedding LookupInterpretabilityMixture of Experts

0 likes · 6 min read

How STEM Replaces MoE Routing with Simple Table Lookup for Faster Transformers

HyperAI Super Neural

Dec 30, 2025 · Artificial Intelligence

Explicit Geological Constraints + Data‑Driven Modeling Improves Cross‑Regional Mineral Prospectivity and Interpretability

Zhejiang University researchers introduce an anisotropic spatial proximity neural network combined with attention‑weighted logistic regression, explicitly embedding geological constraints into mineral prospectivity mapping, and demonstrate superior recall, overall performance, and interpretability across both a classic Canadian gold benchmark and a large‑scale US copper province.

Deep LearningInterpretabilityanisotropic spatial proximity

0 likes · 12 min read

Explicit Geological Constraints + Data‑Driven Modeling Improves Cross‑Regional Mineral Prospectivity and Interpretability

PaperAgent

Dec 29, 2025 · Artificial Intelligence

Unveiling Bottom‑up Policy Optimization: Boosting LLM Reasoning with Internal Strategies

This article introduces Bottom‑up Policy Optimization (BuPO), a novel reinforcement‑learning framework that treats large language models as collections of internal layer and modular policies, revealing distinct inference entropy patterns in Llama and Qwen‑3 and demonstrating superior performance on complex mathematical reasoning benchmarks.

AI researchBottom-up OptimizationInternal Policy

0 likes · 10 min read

Unveiling Bottom‑up Policy Optimization: Boosting LLM Reasoning with Internal Strategies

Bighead's Algorithm Notes

Oct 26, 2025 · Artificial Intelligence

How Shapelet-Based Patterns Predict Financial Market Direction

The article presents a two‑stage framework—SIMPC for invariant multivariate pattern clustering and JISC‑Net for shape‑subclass detection—that achieves accurate and interpretable financial market direction forecasts, outperforming strong baselines on Bitcoin and S&P 500 datasets across most metric‑dataset combinations.

DTWDirection PredictionInterpretability

0 likes · 11 min read

How Shapelet-Based Patterns Predict Financial Market Direction

Data Party THU

Jul 28, 2025 · Artificial Intelligence

How InterpGN Bridges Interpretability and Accuracy in Time Series Classification

InterpGN introduces a novel gated network that combines shapelet‑based interpretable experts with deep neural networks, using confidence‑driven gating to retain transparency on salient samples while delegating complex cases to deep models, achieving state‑of‑the‑art performance and improved shapelet quality across multiple benchmarks, including UEA and MIMIC‑III.

Interpretabilitygated networksshapelets

0 likes · 14 min read

How InterpGN Bridges Interpretability and Accuracy in Time Series Classification

AI Frontier Lectures

Mar 31, 2025 · Artificial Intelligence

How Anthropic’s Path Tracing Reveals the Inner Workings of Claude 3.5 Haiku

Anthropic’s recent paper introduces a path‑tracing technique that uses cross‑layer transcoders and attribution graphs to sparsely visualize and analyze the decision‑making process of the Claude 3.5 Haiku large language model, demonstrating Pareto‑optimal improvements and a four‑stage reverse‑engineering framework while acknowledging current limitations.

AnthropicAttribution GraphClaude 3.5

0 likes · 14 min read

How Anthropic’s Path Tracing Reveals the Inner Workings of Claude 3.5 Haiku

Alibaba Cloud Big Data AI Platform

May 29, 2024 · Artificial Intelligence

ContraLSP: Contrastive Sparse Perturbations Transform Time‑Series Explanation

Recent collaboration between Alibaba Cloud’s big‑data team and leading universities introduced ContraLSP, a novel contrastive and locally sparse perturbation framework that outperforms state‑of‑the‑art methods in explaining time‑series models, offering improved interpretability for both white‑box forecasting and black‑box classification tasks.

Interpretabilitycontrastive learningmachine learning

0 likes · 8 min read

ContraLSP: Contrastive Sparse Perturbations Transform Time‑Series Explanation

AntTech

Apr 17, 2024 · Artificial Intelligence

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

LLMRG introduces a novel framework that leverages large language models to construct personalized reasoning graphs, integrating chain reasoning, self‑verification, divergent extension, and knowledge‑base self‑improvement, thereby enhancing recommendation accuracy, interpretability, and performance across multiple benchmark datasets without additional user or item information.

AIInterpretabilityRecommendation Systems

0 likes · 9 min read

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

DataFunTalk

Mar 14, 2023 · Artificial Intelligence

Review of Deep Learning Model Evolution and Future Trends

The article reviews the past six years of deep‑learning model development, highlighting patterns such as increasing scale, growing universality, limited interpretability, and challenges in efficiency, while forecasting future directions like more efficient architectures, enhanced perception, multimodal capabilities, integration with life sciences, and the emergence of general‑purpose intelligent agents, and concludes with a promotion for a deep‑learning practice ebook.

AI trendsFuture AIInterpretability

0 likes · 6 min read

Review of Deep Learning Model Evolution and Future Trends

Model Perspective

Oct 18, 2022 · Artificial Intelligence

Unlocking Nonlinear Insights: A Practical Guide to Generalized Additive Models (GAM)

Generalized Additive Models (GAM) extend linear regression by using smooth, non‑parametric functions and link functions to capture complex nonlinear relationships, offering flexible estimation via backfitting and local scoring, while balancing interpretability and computational cost, as illustrated through a calcium‑intake health example.

BackfittingGAMInterpretability

0 likes · 8 min read

Unlocking Nonlinear Insights: A Practical Guide to Generalized Additive Models (GAM)

DataFunTalk

Oct 22, 2021 · Artificial Intelligence

Applying AI Techniques to Credit Reporting and Risk Modeling: Model Structure, Pre‑training, Ranking and Interpretability

This article presents a comprehensive overview of how AI technologies are applied to credit reporting and loan risk modeling, detailing data characteristics, end‑to‑end model architectures, pre‑training strategies, risk‑ranking methods, and interpretability techniques for financial risk assessment.

AIInterpretabilityModel Optimization

0 likes · 17 min read

Applying AI Techniques to Credit Reporting and Risk Modeling: Model Structure, Pre‑training, Ranking and Interpretability

DataFunSummit

Oct 22, 2021 · Artificial Intelligence

Applying AI Techniques to Credit Reporting and Risk Modeling

This article presents a comprehensive overview of how AI technologies are applied to credit reporting, covering data characteristics, end‑to‑end model architectures, pre‑training strategies, risk ranking objectives, and interpretability methods to improve financial risk assessment.

AIInterpretabilityModel Optimization

0 likes · 16 min read

Applying AI Techniques to Credit Reporting and Risk Modeling

DataFunTalk

Mar 23, 2021 · Artificial Intelligence

Explainability in Graph Neural Networks: A Taxonomic Survey

This article surveys recent advances in graph neural network explainability, systematically categorizing instance‑level and model‑level methods, reviewing datasets, evaluation metrics, and proposing new benchmark graph datasets for interpretable GNN research, and highlighting future research directions.

GNNInterpretabilitybenchmark datasets

0 likes · 40 min read

Explainability in Graph Neural Networks: A Taxonomic Survey

DataFunTalk

Mar 14, 2021 · Artificial Intelligence

A Review of Medical Domain Sentiment Analysis: Interpretability, Contextual Aspect‑Sentiment Relations, Noisy Labels, and Domain Lexicon Construction

This article reviews recent research on medical sentiment analysis, covering interpretability of neural models, contextual aspect‑sentiment interactions, strategies for handling noisy labels, and methods for building domain‑specific sentiment lexicons, highlighting challenges and proposed solutions.

Deep LearningInterpretabilitySentiment Analysis

0 likes · 19 min read

A Review of Medical Domain Sentiment Analysis: Interpretability, Contextual Aspect‑Sentiment Relations, Noisy Labels, and Domain Lexicon Construction

DataFunTalk

Sep 26, 2020 · Artificial Intelligence

What Makes a Good Model? Understanding Model Concepts, Types, and Evaluation in Data Science

This article explores the definition of a model, distinguishes business, data, and function models, discusses criteria for a good model—including performance, fidelity to real‑world relationships, and interpretability—and examines why a universal model does not exist, all within the context of data science and AI.

AIData ScienceInterpretability

0 likes · 18 min read

What Makes a Good Model? Understanding Model Concepts, Types, and Evaluation in Data Science

Tencent Cloud Developer

Sep 23, 2020 · Artificial Intelligence

NLP Model Interpretability: White-box and Black-box Methods and Business Applications

The article reviews NLP interpretability techniques, contrasting white‑box approaches that probe model internals such as neuron analysis, diagnostic classifiers, and attention with black‑box strategies like rationales, adversarial testing, and local surrogates, and argues that black‑box methods are generally more practical for business deployment despite offering shallower insights.

Attention MechanismBERTDeep Learning

0 likes · 12 min read

NLP Model Interpretability: White-box and Black-box Methods and Business Applications

Alibaba Cloud Developer

Jul 24, 2019 · Artificial Intelligence

Unlocking Better Knowledge Graph Reasoning: The CrossE Model Explained

CrossE introduces an explicit crossover interaction mechanism for knowledge graph embedding, learning both general and interaction-specific representations of entities and relations, which improves link prediction accuracy and provides interpretable explanations, as demonstrated on benchmark datasets WN18, FB15k, and FB15k-237.

EmbeddingInterpretabilityKnowledge Graph

0 likes · 9 min read

Unlocking Better Knowledge Graph Reasoning: The CrossE Model Explained