Cover Image

A Modular Dataset to Demonstrate LLM Abstraction Capability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Atanas, Adam, Liu, Kai
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Demonstrating the Continual Learning Capabilities and Practical Application of Discrete-Time Active Inference
by: Prakki, Rithvik
Published: (2024)

Neural Causal Abstractions
by: Xia, Kevin, et al.
Published: (2024)

Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing
by: Zhang, Yi-Kai, et al.
Published: (2025)

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
by: He, Jinmin, et al.
Published: (2025)

Distributionally Robust Causal Abstractions
by: Felekis, Yorgos, et al.
Published: (2025)

Contrastive Abstraction for Reinforcement Learning
by: Patil, Vihang, et al.
Published: (2024)

Automatic Demonstration Selection for LLM-based Tabular Data Classification
by: Han, Shuchu, et al.
Published: (2025)

Enhancing LLM Planning Capabilities through Intrinsic Self-Critique
by: Bohnet, Bernd, et al.
Published: (2025)

Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction
by: Adeseye, Aisvarya, et al.
Published: (2026)

Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction
by: Cao, Yanan, et al.
Published: (2026)

When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
by: Li, Xinhu, et al.
Published: (2025)

In-Context Planning with Latent Temporal Abstractions
by: Luo, Baiting, et al.
Published: (2026)

Interval Abstractions for Robust Counterfactual Explanations
by: Jiang, Junqi, et al.
Published: (2024)

Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
by: Liu, Hengjie, et al.
Published: (2026)

Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
by: Gao, Hang, et al.
Published: (2025)

Demonstration-Free Robotic Control via LLM Agents
by: Tsui, Brian Y., et al.
Published: (2026)

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
by: Li, Zhuo, et al.
Published: (2026)

Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
by: Wu, Fangzhou, et al.
Published: (2026)

[Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games
by: Pollo, Jorge Carrasco, et al.
Published: (2026)

Vector Symbolic Algebras for the Abstraction and Reasoning Corpus
by: Joffe, Isaac, et al.
Published: (2025)

Abstraction for Offline Goal-Conditioned Reinforcement Learning
by: Wibault, Clarisse, et al.
Published: (2026)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
by: Campbell, Declan, et al.
Published: (2024)

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets
by: Ghosh, Sreejita, et al.
Published: (2022)

CALM: A CKA-Guided Adaptive Layer-Wise Modularization Framework for LLM Quantization
by: Zhang, Jinhao, et al.
Published: (2025)

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning
by: Bushipaka, Praveen, et al.
Published: (2025)

Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks
by: Abed, Amal, et al.
Published: (2025)

Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective
by: Shaj, Vaisakh
Published: (2024)

Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions
by: Nayyar, Rashmeet Kaur, et al.
Published: (2025)

Causal Abstraction Learning based on the Semantic Embedding Principle
by: D'Acunto, Gabriele, et al.
Published: (2025)

Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning
by: Cipollone, Roberto, et al.
Published: (2025)

Policy Gradient Methods in the Presence of Symmetries and State Abstractions
by: Panangaden, Prakash, et al.
Published: (2023)

Learning Markov State Abstractions for Deep Reinforcement Learning
by: Allen, Cameron, et al.
Published: (2021)

Can Active Label Correction Improve LLM-based Modular AI Systems?
by: Taneja, Karan, et al.
Published: (2024)

Preference-Conditioned Language-Guided Abstraction
by: Peng, Andi, et al.
Published: (2024)

Learning with Language-Guided State Abstractions
by: Peng, Andi, et al.
Published: (2024)

ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
by: Moffitt, Michael D.
Published: (2025)

A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions
by: Amar, Mohamed Mahmoud, et al.
Published: (2026)

Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids
by: Xiao, Qingyu, et al.
Published: (2025)

Combining Causal Models for More Accurate Abstractions of Neural Networks
by: Pîslar, Theodora-Mara, et al.
Published: (2025)

Learning with Expert Abstractions for Efficient Multi-Task Continuous Control
by: Jewett, Jeff, et al.
Published: (2025)