Imagen de Portada

EvoLM: In Search of Lost Language Model Training Dynamics

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qi, Zhenting, Nie, Fan, Alahi, Alexandre, Zou, James, Lakkaraju, Himabindu, Du, Yilun, Xing, Eric, Kakade, Sham, Zhang, Hanlin
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
por: Qi, Zhenting, et al.
Publicado: (2024)

Self-Improving Language Models with Bidirectional Evolutionary Search
por: Xu, Guowei, et al.
Publicado: (2026)

A Study on the Calibration of In-context Learning
por: Zhang, Hanlin, et al.
Publicado: (2023)

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
por: Li, Shuyue Stella, et al.
Publicado: (2026)

Peer-Predictive Self-Training for Language Model Reasoning
por: Feng, Shi, et al.
Publicado: (2026)

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
por: Xiong, Zidi, et al.
Publicado: (2025)

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
por: Pawelczyk, Martin, et al.
Publicado: (2024)

Scaling Reward Modeling without Human Supervision
por: Fan, Jingxuan, et al.
Publicado: (2026)

Quantifying Generalization Complexity for Large Language Models
por: Qi, Zhenting, et al.
Publicado: (2024)

Manipulating Large Language Models to Increase Product Visibility
por: Kumar, Aounon, et al.
Publicado: (2024)

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
por: Wu, Tianyu, et al.
Publicado: (2026)

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
por: Zhang, Hanlin, et al.
Publicado: (2026)

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
por: Jin, Jikai, et al.
Publicado: (2025)

Learning Recourse Costs from Pairwise Feature Comparisons
por: Rawal, Kaivalya, et al.
Publicado: (2024)

Towards Uncovering How Large Language Model Works: An Explainability Perspective
por: Zhao, Haiyan, et al.
Publicado: (2024)

In-Context Unlearning: Language Models as Few Shot Unlearners
por: Pawelczyk, Martin, et al.
Publicado: (2023)

Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants
por: Morwani, Depen, et al.
Publicado: (2025)

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models
por: Agarwal, Chirag, et al.
Publicado: (2024)

CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
por: Brandfonbrener, David, et al.
Publicado: (2024)

Understanding the Effects of Iterative Prompting on Truthfulness
por: Krishna, Satyapriya, et al.
Publicado: (2024)

Characterizing Data Point Vulnerability via Average-Case Robustness
por: Han, Tessa, et al.
Publicado: (2023)

Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
por: Xiong, Zidi, et al.
Publicado: (2026)

On the Impact of Fine-Tuning on Chain-of-Thought Reasoning
por: Lobo, Elita, et al.
Publicado: (2024)

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
por: Bhalla, Usha, et al.
Publicado: (2023)

On the Trade-offs between Adversarial Robustness and Actionable Explanations
por: Krishna, Satyapriya, et al.
Publicado: (2023)

Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
por: Huang, Catherine, et al.
Publicado: (2024)

Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
por: Song, Yuda, et al.
Publicado: (2024)

Selective Underfitting in Diffusion Models
por: Song, Kiwhan, et al.
Publicado: (2025)

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
por: Han, Tessa, et al.
Publicado: (2024)

Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications
por: Liu, Yanchen, et al.
Publicado: (2023)

Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
por: Zhang, Shichang, et al.
Publicado: (2025)

On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
por: Tanneru, Sree Harsha, et al.
Publicado: (2024)

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors
por: Nie, Fan, et al.
Publicado: (2025)

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness
por: Li, Aaron J., et al.
Publicado: (2024)

TAROT: Targeted Data Selection via Optimal Transport
por: Feng, Lan, et al.
Publicado: (2024)

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
por: Zhang, Shichang, et al.
Publicado: (2025)

Towards Unifying Interpretability and Control: Evaluation via Intervention
por: Bhalla, Usha, et al.
Publicado: (2024)

Interpretability Needs a New Paradigm
por: Madsen, Andreas, et al.
Publicado: (2024)

Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers
por: Oesterling, Alex, et al.
Publicado: (2024)

Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models
por: Jelassi, Samy, et al.
Publicado: (2026)