Fine-tuning

Feeds to Scour
SubscribedAll
Scoured 99 posts in 50.3 ms

Sequential Data Poisoning in LLM Post-Training

 🔥Burn  Content type: Academic
arxiv.org·

SecLoRA: Secure Aggregation of Low-Rank Matrix Products via Functional Encryption

 🔐Cryptography
eprint.iacr.org·
Less-relevant results

If Claude Fable stops helping you, you'll never know

 🧭Content Discovery  Content type: Blog
jonready.com··Lobsters, Hacker News

GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)

 🗄️Database Internals

The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning

 🎯BM25  Content type: Academic
arxiv.org·

Alignment Defends LLMs from Property Inference Attacks

 🌲LSM Trees  Content type: Academic
arxiv.org·

Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization

 🌲LSM Trees  Content type: Academic
arxiv.org·

Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

 💬Natural Language Processing  Content type: Academic
arxiv.org·

Parameter-Efficient Fine-Tuning with Learnable Rank

 💬Natural Language Processing  Content type: Academic
arxiv.org·

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

 📐Embeddings  Content type: Academic
arxiv.org·

Emergence of Context Characteristics Sensitivity in Large Language Models

 📐Embeddings  Content type: Academic
arxiv.org·

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

 🎲Procedural Generation  Content type: Academic
arxiv.org·

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

 🌲LSM Trees  Content type: Academic
arxiv.org·

PEFT of SLM for Telecommunications Customer Support: A Comparative Study of LoRA Configurations with Energy Consumption Analysis

 🧠Query Planners  Content type: Academic
arxiv.org·

PriFT: Prior-Support Guided Supervised Fine-Tuning

 ⚙️Compilers  Content type: Academic
arxiv.org·

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks

 🔥Burn  Content type: Academic
arxiv.org·

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model

 👤Search Personalization  Content type: Academic
arxiv.org·

Emergent alignment and the projectability of ethical personas

 📰Content Curation  Content type: Academic
arxiv.org·

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

 💬Natural Language Processing  Content type: Academic
arxiv.org·

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

 🎯Recommendation Algorithms  Content type: Academic
arxiv.org·

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