Image de couverture de livre

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Quanen, Tian, Changxin, Shi, Ke, Chen, Cai, Peng, Cunyin, Liu, Jia, Chen, Kunlong, Zhang, Zhiqiang
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models
par: Tian, Changxin, et autres
Publié: (2025)

Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
par: Chen, Sirui, et autres
Publié: (2025)

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
par: Wang, Jiapeng, et autres
Publié: (2025)

Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law
par: Ge, Qiming, et autres
Publié: (2025)

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training
par: Tian, Changxin, et autres
Publié: (2025)

PowLU: An Activation Function for Stable Pre-Training of LLMs
par: Jiang, Peijie, et autres
Publié: (2026)

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
par: Xu, Chengyin, et autres
Publié: (2025)

Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks
par: Zhang, Yichi, et autres
Publié: (2024)

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
par: Schaeffer, Rylan, et autres
Publié: (2024)

Automated Essay Scoring and Language Certification: Assessing Generalizability, Agreement and Validity for French
par: Wilkens, Rodrigo, et autres
Publié: (2026)

Scaling Laws for Predicting Downstream Performance in LLMs
par: Chen, Yangyi, et autres
Publié: (2024)

Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking
par: Zhang, Yichi, et autres
Publié: (2024)

OntoTune: Ontology-Driven Self-training for Aligning Large Language Models
par: Liu, Zhiqiang, et autres
Publié: (2025)

BOSE: A Systematic Evaluation Method Optimized for Base Models
par: Luan, Hongzhi, et autres
Publié: (2025)

Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG
par: Triantafyllopoulos, Ilias, et autres
Publié: (2025)

RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models
par: Rodriguez, Juan Diego, et autres
Publié: (2025)

Measuring Aleatoric and Epistemic Uncertainty in LLMs: Empirical Evaluation on ID and OOD QA Tasks
par: Wang, Kevin, et autres
Publié: (2025)

Scaling Agentic Capabilities via Grounded Interaction Synthesis
par: Shi, Wenhang, et autres
Publié: (2026)

Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models
par: Deng, Guanzhi, et autres
Publié: (2026)

DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training
par: Tian, Xiaoyu, et autres
Publié: (2025)

Paraphrase-Aligned Machine Translation
par: Chang, Ke-Ching, et autres
Publié: (2024)

Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF
par: Zheng, Chen, et autres
Publié: (2024)

I run as fast as a rabbit, can you? A Multilingual Simile Dialogue Dataset
par: Ma, Longxuan, et autres
Publié: (2023)

Criterion Validity of LLM-as-Judge for Business Outcomes in Conversational Commerce
par: Chen, Liang, et autres
Publié: (2026)

LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach
par: Chen, Kunlong, et autres
Publié: (2024)

M-Eval: A Heterogeneity-Based Framework for Multi-evidence Validation in Medical RAG Systems
par: Sun, Mengzhou, et autres
Publié: (2025)

Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check
par: Lourie, Nicholas, et autres
Publié: (2025)

Scaling Laws for Downstream Task Performance of Large Language Models
par: Isik, Berivan, et autres
Publié: (2024)

Are Large Language Models Capable of Generating Human-Level Narratives?
par: Tian, Yufei, et autres
Publié: (2024)

Reasons to Reject? Aligning Language Models with Judgments
par: Xu, Weiwen, et autres
Publié: (2023)

TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models
par: Zhang, Chen, et autres
Publié: (2024)

Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions
par: Liu, Emmy, et autres
Publié: (2025)

Optimising Language Models for Downstream Tasks: A Post-Training Perspective
par: Shi, Zhengyan
Publié: (2025)

Logic Agent: Enhancing Validity with Logic Rule Invocation
par: Liu, Hanmeng, et autres
Publié: (2024)

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
par: P Team, et autres
Publié: (2025)

AlignCap: Aligning Speech Emotion Captioning to Human Preferences
par: Liang, Ziqi, et autres
Publié: (2024)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
par: Wang, Jiapeng, et autres
Publié: (2026)

Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents
par: Safa, Abdulfattah, et autres
Publié: (2024)

EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI
par: Zuo, Longfei, et autres
Publié: (2025)

Advancing Automated In-Isolation Validation in Repository-Level Code Translation
par: Ke, Kaiyao, et autres
Publié: (2025)