Methods › Reinforcement Learning › Reinforcement Learning Frameworks › RLAIF
Reinforcement Learning from AI Feedback
RLAIF
Introduced by Daechul Ahn et al. in Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
In Syntology the paper matched by title, the paper Syntology's graph keys as openreview_AAxIs3D2ZZ, held, no code (no_code; paper_only). The lookup matched a paper by its title, the paper Syntology's graph keys as openreview_AAxIs3D2ZZ, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about the paper Syntology's graph keys as openreview_AAxIs3D2ZZ) is about this method is not checked; it does not say whether this method has code.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 19 · with a code link: 9 · where Syntology ran a sample: 5 (3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 19 tagged: 3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 19 of 19, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models 28 Apr 2025 · 1 repository · arXiv:2504.20157Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 15 pointer-only (licence)
-
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation 7 Apr 2025 · 1 repository · arXiv:2504.04699
-
Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use 7 Apr 2025 · 0 repositories · arXiv:2504.04736
-
Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression 22 Jan 2025 · 0 repositories · arXiv:2501.12698
-
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment 17 Oct 2024 · 0 repositories · arXiv:2410.13785
-
Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment 5 Oct 2024 · 0 repositories · arXiv:2410.04112
-
Generative Reward Models 2 Oct 2024 · 0 repositories · arXiv:2410.12832
-
MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models 30 Aug 2024 · 1 repository · arXiv:2408.17072
-
Applying RLAIF for Code Generation with API-usage in Lightweight LLMs 28 Jun 2024 · 0 repositories · arXiv:2406.20060
-
Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback 27 Jun 2024 · 0 repositories · arXiv:2407.09551
-
Multi-objective Reinforcement learning from AI Feedback 11 Jun 2024 · 1 repository · arXiv:2406.07295
-
Are You Sure? Rank Them Again: Repeated Ranking For Better Preference Datasets 29 May 2024 · 0 repositories · arXiv:2405.18952
-
Optimization-based Prompt Injection Attack to LLM-as-a-Judge 26 Mar 2024 · 1 repository · arXiv:2403.17710Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences 14 Mar 2024 · 2 repositories · arXiv:2403.09032Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback 13 Mar 2024 · 0 repositories · arXiv:2403.08309
-
A Critical Evaluation of AI Feedback for Aligning Large Language Models 19 Feb 2024 · 1 repository · arXiv:2402.12366Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples) · 1 pointer-only (licence)
-
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation 19 Feb 2024 · 1 repository · arXiv:2402.11907Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models 16 Feb 2024 · 0 repositories · arXiv:2402.10986
-
Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback 6 Feb 2024 · 1 repository · arXiv:2402.03746
Tasks archive 2025-07-28
20 shown of 34 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections