Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
post-training alignment
Description:
The process of adapting an already-trained artificial intelligence model to better follow human intentions, preferences, or safety requirements.
Related topics:
Topic Modeling (17%),
Ethics and Social Impacts of AI (13%),
Generative Adversarial Networks and Image Synthesis (9%),
Multimodal Machine Learning Applications (9%)
OpenAlex ID:
keywords/post-training-alignment
GPT-4 Technical Report
2023
·
OpenAI
, Achiam, Josh
, et al.
·
arXiv (Cornell University)
·
56,588
PDF
Relying on the Unreliable: The Impact of Language Models’ Reluctance to Express Uncertainty
2024
·
Kaitlyn Zhou
, Jena Hwang
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
217
PDF
Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
2025
·
Zhang, Jiayi
, Yu, Simon
, et al.
·
arXiv (Cornell University)
·
175
PDF
Can LLM Graph Reasoning Generalize beyond Pattern Memorization?
2024
·
Yizhuo Zhang
, Heng Wang
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
·
80
PDF
Reconstruction Alignment Improves Unified Multimodal Models
2026
·
Xie, Ji
, Darrell, Trevor
, et al.
·
International Conference on Learning Representations
·
56
PDF
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
2024
·
Ji, Jiaming
, Zhou, Jiayi
, et al.
·
arXiv (Cornell University)
·
52
PDF
Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
2026
·
Tice, Cameron
, Radmard, Puria
, et al.
·
arXiv (Cornell University)
·
42
PDF
Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
2025
·
Maiya, Sharan
, Bartsch, Henning
, et al.
·
arXiv (Cornell University)
·
34
PDF
PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips
2024
·
Coalson, Zachary
, Woo, Jeonghyun
, et al.
·
arXiv (Cornell University)
·
32
PDF
SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
2026
·
Zhang, Xueyao
, Wang, Chaoren
, et al.
·
International Conference on Learning Representations
·
27
PDF
CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling
2025
·
Taneesh Gupta
, Shivam Shandilya
, et al.
·
Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
·
25
PDF
Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
2024
·
Zhang, Daoan
, Lan, Guangchen
, et al.
·
arXiv (Cornell University)
·
21
PDF
Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM
2025
·
Alnumay, Yazeed
, Barbet, Alexandre
, et al.
·
arXiv (Cornell University)
·
19
PDF
Aligning CodeLLMs with Direct Preference Optimization
2024
·
Miao, Yibo
, Gao, Bofei
, et al.
·
arXiv (Cornell University)
·
15
PDF
Manifold-Aware Exploration for Reinforcement Learning in Video Generation
2026
·
Zheng, Mingzhe
, Kong, Weijie
, et al.
·
arXiv (Cornell University)
·
14
PDF
An Overview of Recent Advances in Natural Language Processing for Information Systems
2026
·
Douglas O'Shaughnessy
·
Applied Sciences
·
14
PDF
Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging
2026
·
Tiancheng Hu
, Benjamin Minixhofer
, et al.
·
Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
·
12
PDF
Aligning Model Properties via Conformal Risk Control
2024
·
William Overman
, Jacqueline Vallon
, et al.
·
neural information processing systems
·
12
Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
2026
·
Atsumoto Ohashi
, Neil Zeghidour
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
11
PDF
Synth-Align: Improving Trustworthiness in Vision-Language Model with Synthetic Preference Data Alignment
2024
·
Wijaya, Robert
, Nguyen, Ngoc-Bao
, et al.
·
arXiv (Cornell University)
·
10
PDF
Entropy Controllable Direct Preference Optimization
2024
·
Omura, Motoki
, Fujita, Yasuhiro
, et al.
·
arXiv (Cornell University)
·
10
PDF
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
2026
·
Qin, You
, Wang, Linqing
, et al.
·
arXiv (Cornell University)
·
9
PDF
What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
2026
·
Hou, Zhinan
, Zhang, Jiaqi
, et al.
·
arXiv (Cornell University)
·
8
PDF
Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
2025
·
Blondel, Mathieu
, Sander, Michael E.
, et al.
·
arXiv (Cornell University)
·
8
PDF
FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning
2026
·
Haoxu Wang
, Biao Tian
, et al.
·
IEEE International Conference on Acoustics Speech and Signal Processing
·
7
PDF
Show more works
View as search
Works count:
152
Citation count:
57,680
Year
Topic
Type