Cover Image

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hase, Peter, Bansal, Mohit, Clark, Peter, Wiegreffe, Sarah
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mechanistic?
by: Saphra, Naomi, et al.
Published: (2024)

The Unreasonable Effectiveness of Eccentric Automatic Prompts
by: Battle, Rick, et al.
Published: (2024)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
by: Gambardella, Andrew, et al.
Published: (2024)

Effective Reasoning Chains Reduce Intrinsic Dimensionality
by: Prasad, Archiki, et al.
Published: (2026)

System-1.x: Learning to Balance Fast and Slow Planning with Language Models
by: Saha, Swarnadeep, et al.
Published: (2024)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
by: Cheng, Stephen, et al.
Published: (2026)

Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
by: Parashar, Shubham, et al.
Published: (2025)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Teaching Models to Balance Resisting and Accepting Persuasion
by: Stengel-Eskin, Elias, et al.
Published: (2024)

ADaPT: As-Needed Decomposition and Planning with Language Models
by: Prasad, Archiki, et al.
Published: (2023)

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
by: Maharana, Adyasha, et al.
Published: (2023)

Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression
by: Xiao, Hanqi, et al.
Published: (2025)

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
by: Khan, Zaid, et al.
Published: (2024)

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
by: Sun, Zhiqing, et al.
Published: (2024)

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents
by: Zala, Abhay, et al.
Published: (2024)

Are language models rational? The case of coherence norms and belief revision
by: Hofweber, Thomas, et al.
Published: (2024)

The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs
by: Bandarkar, Lucas, et al.
Published: (2025)

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings
by: Jiang, Yichen, et al.
Published: (2024)

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
by: Chen, Justin Chih-Yao, et al.
Published: (2026)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
by: Ding, Mucong, et al.
Published: (2024)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
by: Patil, Vaidehi, et al.
Published: (2025)

MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
by: Zhang, Shiyue, et al.
Published: (2023)

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
by: Chen, Justin Chih-Yao, et al.
Published: (2023)

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
by: Yadav, Prateek, et al.
Published: (2023)

Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?
by: Hase, Peter, et al.
Published: (2024)

Soft Self-Consistency Improves Language Model Agents
by: Wang, Han, et al.
Published: (2024)

Multi-Attribute Steering of Language Models via Targeted Intervention
by: Nguyen, Duy, et al.
Published: (2025)

Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training
by: Wan, David, et al.
Published: (2024)

Counterfactual Simulation Training for Chain-of-Thought Faithfulness
by: Hase, Peter, et al.
Published: (2026)

Zero-Training Temporal Drift Detection for Transformer Sentiment Models: A Comprehensive Analysis on Authentic Social Media Streams
by: Bansal, Aayam, et al.
Published: (2025)

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
by: Khan, Zaid, et al.
Published: (2025)

One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
by: Khan, Zaid, et al.
Published: (2025)

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
by: Sung, Yi-Lin, et al.
Published: (2025)

ReGAL: Refactoring Programs to Discover Generalizable Abstractions
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Is Child-Directed Speech Effective Training Data for Language Models?
by: Feng, Steven Y., et al.
Published: (2024)

Branch-Solve-Merge Improves Large Language Model Evaluation and Generation
by: Saha, Swarnadeep, et al.
Published: (2023)

FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline
by: Seegmiller, Parker, et al.
Published: (2025)

Anyprefer: An Agentic Framework for Preference Data Synthesis
by: Zhou, Yiyang, et al.
Published: (2025)

Data-driven Discovery with Large Generative Models
by: Majumder, Bodhisattwa Prasad, et al.
Published: (2024)

Evaluating Very Long-Term Conversational Memory of LLM Agents
by: Maharana, Adyasha, et al.
Published: (2024)