RLHF

🎯 RLHFSpecific

Reinforcement Learning from Human Feedback, Reward Modeling, Preference Learning, Alignment

Feeds to Scour
SubscribedAll
Scoured 76 posts in 7.2 ms

Emergence of Context Characteristics Sensitivity in Large Language Models

 ⚙post training infra  Content type: Academic
arxiv.org·

Variational Proximal Policy Optimization

 🎭Mixture of Experts  Content type: Academic
arxiv.org·

DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment

 ⚙post training infra  Content type: Academic
arxiv.org·
Less-relevant results

Turkish Navy Confirms 2032 Delivery Date for MUGEM Aircraft Carrier

 ⚙post training infra
navalnews.com·

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output

 ⚙post training infra  Content type: Academic
arxiv.org·

PayPal and Hey Savi Launch UK’s First Agentic Commerce Platform, Debenhams Group Signs On

 🤖agentic system
easternherald.com·

(VERY PARTIAL) CROSSPOST: ALEX HEATH: SubStack Is Opening Up to AI: Interviewing CEO Chris Best

 ⚙post training infra  Content type: News  Content type: Blog
braddelong.substack.com
··Substack

Multilingual Refusal Alignment for Safer Large Language Models

 📊LLM Evaluation  Content type: Academic
arxiv.org·

PAFO: Pareto Fairness Optimization for Personalized Reward Modeling

 ⚙post training infra  Content type: Academic
arxiv.org·

Substrate Asymmetry in User-Side Memory: A Diagnostic Framework

 🎛️Fine-Tuning  Content type: Academic
arxiv.org·

Harmfulness Directions in OLMo

 ⚙post training infra
lesswrong.com·

A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales

 📊LLM Evaluation  Content type: Academic
arxiv.org·

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

 ⚙post training infra  Content type: Academic
arxiv.org·

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models

 ⚙post training infra  Content type: Academic
arxiv.org·

Emergent alignment and the projectability of ethical personas

 🎛️Fine-Tuning  Content type: Academic
arxiv.org·

What Do People Actually Want From AI? Mapping Preference Plurality

 ⚙post training infra  Content type: Academic
arxiv.org·

Mechanistic Analysis of Alignment Algorithms in Language Models

 ⚙post training infra  Content type: Academic
arxiv.org·

Korean Culture into LLM Alignment: Toward Cultural Coherence

 ⚙post training infra  Content type: Academic
arxiv.org·

Hidden Consensus:Preference-Validity Compression in Human Feedback

 ⚙post training infra  Content type: Academic
arxiv.org·

Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach

 ⚙post training infra  Content type: Academic
arxiv.org·
Sign up or log in to see more results
Sign UpLogin

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help