LLM Interpretability with Identifiable Temporal-Instantaneous Representation
Fuente:
arXiv
Saved in:
| Main Authors: | Song, Xiangchen, Sun, Jiaqi, Li, Zijian, Zheng, Yujia, Zhang, Kun |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
On the Identification of Temporally Causal Representation with Instantaneous Dependence
by: Li, Zijian, et al.
Published: (2024)
by: Li, Zijian, et al.
Published: (2024)
Causal Temporal Representation Learning with Nonstationary Sparse Transition
by: Song, Xiangchen, et al.
Published: (2024)
by: Song, Xiangchen, et al.
Published: (2024)
Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
by: Kong, Lingjing, et al.
Published: (2025)
by: Kong, Lingjing, et al.
Published: (2025)
Towards Identifiability of Hierarchical Temporal Causal Representation Learning
by: Li, Zijian, et al.
Published: (2025)
by: Li, Zijian, et al.
Published: (2025)
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
by: Song, Xiangchen, et al.
Published: (2025)
by: Song, Xiangchen, et al.
Published: (2025)
A General Representation-Based Approach to Multi-Source Domain Adaptation
by: Ng, Ignavier, et al.
Published: (2026)
by: Ng, Ignavier, et al.
Published: (2026)
Temporally Disentangled Representation Learning under Unknown Nonstationarity
by: Song, Xiangchen, et al.
Published: (2023)
by: Song, Xiangchen, et al.
Published: (2023)
On the Identifiability of Nonlinear ICA: Sparsity and Beyond
by: Zheng, Yujia, et al.
Published: (2022)
by: Zheng, Yujia, et al.
Published: (2022)
Identifying Selections for Unsupervised Subtask Discovery
by: Qiu, Yiwen, et al.
Published: (2024)
by: Qiu, Yiwen, et al.
Published: (2024)
On the Identifiability of Sparse ICA without Assuming Non-Gaussianity
by: Ng, Ignavier, et al.
Published: (2024)
by: Ng, Ignavier, et al.
Published: (2024)
CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
by: Chen, Guangyi, et al.
Published: (2024)
by: Chen, Guangyi, et al.
Published: (2024)
Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal Models
by: Dong, Xinshuai, et al.
Published: (2025)
by: Dong, Xinshuai, et al.
Published: (2025)
Type Information-Assisted Self-Supervised Knowledge Graph Denoising
by: Sun, Jiaqi, et al.
Published: (2025)
by: Sun, Jiaqi, et al.
Published: (2025)
Calibration-then-Calculation: A Variance Reduced Metric Framework in Deep Click-Through Rate Prediction Models
by: Fan, Yewen, et al.
Published: (2024)
by: Fan, Yewen, et al.
Published: (2024)
Causal Representation Learning from Multiple Distributions: A General Setting
by: Zhang, Kun, et al.
Published: (2024)
by: Zhang, Kun, et al.
Published: (2024)
Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
by: Li, Zijian, et al.
Published: (2025)
by: Li, Zijian, et al.
Published: (2025)
Diverse Dictionary Learning
by: Zheng, Yujia, et al.
Published: (2026)
by: Zheng, Yujia, et al.
Published: (2026)
Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
by: Li, Zijian, et al.
Published: (2024)
by: Li, Zijian, et al.
Published: (2024)
From Generalist to Specialist Representation
by: Zheng, Yujia, et al.
Published: (2026)
by: Zheng, Yujia, et al.
Published: (2026)
Partial Identifiability for Domain Adaptation
by: Kong, Lingjing, et al.
Published: (2023)
by: Kong, Lingjing, et al.
Published: (2023)
Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families
by: Hulsman, Roel, et al.
Published: (2026)
by: Hulsman, Roel, et al.
Published: (2026)
Detecting and Identifying Selection Structure in Sequential Data
by: Zheng, Yujia, et al.
Published: (2024)
by: Zheng, Yujia, et al.
Published: (2024)
Causal Representation Learning from Multimodal Biomedical Observations
by: Sun, Yuewen, et al.
Published: (2024)
by: Sun, Yuewen, et al.
Published: (2024)
Thought Communication in Multiagent Collaboration
by: Zheng, Yujia, et al.
Published: (2025)
by: Zheng, Yujia, et al.
Published: (2025)
Nonparametric Identification of Latent Concepts
by: Zheng, Yujia, et al.
Published: (2025)
by: Zheng, Yujia, et al.
Published: (2025)
DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning
by: Li, Deyi, et al.
Published: (2026)
by: Li, Deyi, et al.
Published: (2026)
SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs
by: Das, Sourajit, et al.
Published: (2026)
by: Das, Sourajit, et al.
Published: (2026)
Understanding Catastrophic Interference: On the Identifibility of Latent Representations
by: Li, Yuke, et al.
Published: (2025)
by: Li, Yuke, et al.
Published: (2025)
Long-Term Individual Causal Effect Estimation via Identifiable Latent Representation Learning
by: Cai, Ruichu, et al.
Published: (2025)
by: Cai, Ruichu, et al.
Published: (2025)
Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?
by: Yang, Hongzheng, et al.
Published: (2025)
by: Yang, Hongzheng, et al.
Published: (2025)
FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
by: Yao, Yuan, et al.
Published: (2025)
by: Yao, Yuan, et al.
Published: (2025)
Multi-Modality Spatio-Temporal Forecasting via Self-Supervised Learning
by: Deng, Jiewen, et al.
Published: (2024)
by: Deng, Jiewen, et al.
Published: (2024)
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
by: Feng, Fan, et al.
Published: (2026)
by: Feng, Fan, et al.
Published: (2026)
Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
by: Li, Changming, et al.
Published: (2026)
by: Li, Changming, et al.
Published: (2026)
CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
by: Chen, Guangyi, et al.
Published: (2025)
by: Chen, Guangyi, et al.
Published: (2025)
InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
by: Fu, Yonggan, et al.
Published: (2021)
by: Fu, Yonggan, et al.
Published: (2021)
Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
by: Welch, Ryan, et al.
Published: (2024)
by: Welch, Ryan, et al.
Published: (2024)
Not only where, But when: Temporal Scheduling for RLVR
by: Zhang, Jinghao, et al.
Published: (2026)
by: Zhang, Jinghao, et al.
Published: (2026)
Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics
by: Nie, Weizhi, et al.
Published: (2026)
by: Nie, Weizhi, et al.
Published: (2026)
ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting
by: Zheng, Qi, et al.
Published: (2024)
by: Zheng, Qi, et al.
Published: (2024)
Similar Items
-
On the Identification of Temporally Causal Representation with Instantaneous Dependence
by: Li, Zijian, et al.
Published: (2024) -
Causal Temporal Representation Learning with Nonstationary Sparse Transition
by: Song, Xiangchen, et al.
Published: (2024) -
Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
by: Kong, Lingjing, et al.
Published: (2025) -
Towards Identifiability of Hierarchical Temporal Causal Representation Learning
by: Li, Zijian, et al.
Published: (2025) -
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
by: Song, Xiangchen, et al.
Published: (2025)