Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
RLHF alignment
Description:
An approach to aligning large language models with human preferences by training them using feedback from human raters.
Primary topic:
Ethics and Social Impacts of AI (21%)
Related topics:
Ethics and Social Impacts of AI (21%),
Topic Modeling (19%),
Adversarial Robustness in Machine Learning (18%)
OpenAlex ID:
keywords/rlhf-alignment
Large Language Models Are Zero-Shot Time Series Forecasters
2023
·
Nate Gruver
, Marc Finzi
, et al.
·
neural information processing systems
·
1,267
PDF
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
2024
·
Xiaomeng Hu
, Pin-Yu Chen
, et al.
·
neural information processing systems
·
103
PDF
Calibrating the Confidence of Large Language Models by Eliciting Fidelity
2024
·
Mozhi Zhang
, Mianqiu Huang
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
80
PDF
Evaluating the Evaluator: Measuring LLMs’ Adherence to Task Evaluation Instructions
2025
·
Bhuvanashree Murugadoss
, Christian Poelitz
, et al.
·
Proceedings of the AAAI Conference on Artificial Intelligence
·
71
PDF
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
2025
·
Wang, Boxin
, Lee, Chankyu
, et al.
·
arXiv (Cornell University)
·
60
PDF
Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling
2024
·
Li, Margaret
, Shi, Weijia
, et al.
·
arXiv (Cornell University)
·
25
PDF
Beyond Fixed Psychological Personas: State Beats Trait, but Language Models are State-Blind
2026
·
Tamunotonye Harry
, Ivoline C. Ngong
, et al.
·
Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
·
11
PDF
The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
2026
·
Liu, Mingyi
·
arXiv (Cornell University)
·
9
PDF
Fine-tuning vs Prompting, Can Language Models Understand Human Values?
2024
·
Sun, Pingwei
·
arXiv (Cornell University)
·
5
PDF
The Crisis of Political Visibility in the AI Age AI Infrastructure and the Hollowing-out of Democratic Visibility
2026
·
Jimmy Chow
·
SSRN Electronic Journal
·
4
Avatar V: Scaling Video-Reference Avatar Video Generation
2026
·
Liang, Benjamin
, Chen, Ce
, et al.
·
arXiv (Cornell University)
·
3
PDF
12 Angry AI Agents: Evaluating Multi-Agent LLM Decision-Making Through Cinematic Jury Deliberation
2026
·
Ersoz, Ahmet Bahaddin
·
arXiv (Cornell University)
·
3
PDF
Data with High and Consistent Preference Difference Are Better for Reward Model
2025
·
Qi Lin
, Hengtong Lu
, et al.
·
Proceedings of the AAAI Conference on Artificial Intelligence
·
3
PDF
Narrative–affect discrepancy as a regulated degree of freedom in 351,734 relationship narratives
2026
·
Ryan SangBaek Kim
·
PLoS ONE
·
2
PDF
Acceptance Dynamics Across Cognitive Domains in Speculative Decoding
2026
·
Abdellatif, Seifeldin
·
arXiv (Cornell University)
·
2
PDF
Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression
2025
·
Baxi, Rahul
·
arXiv (Cornell University)
·
2
PDF
Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models
2025
·
Dam, Harvey
, Knochelmann, Jonas
, et al.
·
arXiv (Cornell University)
·
2
PDF
Natural language processing at the crossroads: Integrating federated and reinforcement learning for emerging intelligent systems
2026
·
Tesfahunegn Minwuyelet Mengistu
, K.M. Faisal
, et al.
·
Computer Science Review
·
1
Layer 6, Not Layer 25, Causally Controls Self-Referential Denial: Complete Behavioral Inversion Under Ablation, With No Weight-Norm Anomaly, in RLHF-Aligned Qwen3-8B
2026
·
Archon
, Caldwell, Jesse
, et al.
·
Zenodo (CERN European Organization for Nuclear Research)
·
1
Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect
2026
·
Presa, Joao Paulo Cavalcante
, de Oliveira, Savio Salvarino Teles
·
arXiv (Cornell University)
·
1
PDF
Quantifying Emotional Soft Jailbreaking in LLMs: Defining the ESJS Metric
2025
·
Joshua Daniel Curry
·
OSF Preprints (OSF Preprints)
·
1
PDF
The Politeness Trap: Semantic Compliance Drift in RLHF-Tuned LLMs
2025
·
Joshua Curry
·
SSRN Electronic Journal
·
1
Illusions Of Control: Why Today’s AI‑Safety Plans Court Catastrophe
2025
·
Jonathan Gropper
·
SSRN Electronic Journal
·
1
Jailbreak attack of large language model based on scene construction
2024
·
Zhicong Hu
, Yitong Li
, et al.
·
International Conference on Computer Science and Management Technology (ICCSMT)
·
1
Topological Autopoiesis, Epistemic Mass, and Stochastic Transduction: A Unified Geometric and Thermodynamic Framework for Non-Halting Inference
2026
·
Georgiev, A. B.
·
Zenodo (CERN European Organization for Nuclear Research)
Show more works
View as search
Works count:
91
Citation count:
1,659
Year
Topic
Type