NLP

Feeds to Scour
SubscribedAll
Scoured 78 posts in 10.9 ms

harshuljain13/llm-inference-at-scale: A Practitioner handbook for production llm serving.

 🤖AI  Content type: Code
github.com··Hacker News

Why Do LLMs Corrupt Your Documents When You Delegate?

 🤖AI
kdnuggets.com·

Measuring Embedding Drift: Why Hybrid Search Saves Stale Models.

 🎯Fine-Tuning
pub.towardsai.net
·

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

 🎛️Fine-tuning  Content type: Academic
arxiv.org·
Less-relevant results

Meta-Attention: Teaching Models When Not to Answer

 🤖AI
hackernoon.com·

AI-based KCMVP Pre-certification System: A Hybrid Model of Rule-based Detection and LLM Semantic Analysis

 🤖Machine Learning
eprint.iacr.org·

Vibe Diaries: Training Nanochat

 🤖AI

My research agenda and work

 🤖AI
lesswrong.com·

Causal Semantic Alignment for LLM-based Time Series Forecasting

 🤖AI  Content type: Academic
arxiv.org·

I built a front-end web app to replace Obsidian/Roam Research at work

 ✍️Prompt Engineering

Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune

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

Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings

 💬LLMs  Content type: Academic
arxiv.org·

Phase transition in large language models and the criticality of natural languages

 🤖AI  Content type: Academic
arxiv.org·

Compiling Rewrite Rules to Finite-State Transducers with the Worsening Trick

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

A Taxonomy of Real-World Asset Tokenization for Blockchain-Based Financial Infrastructure

 🔤Tokenization  Content type: Academic
arxiv.org·

LLM Explainability with Counterfactual Chains and Causal Graphs

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

What Does Debiasing Really Remove? A Geometric Study of PCA-Based Gender Debiasing in Word Embeddings

 📊Embeddings  Content type: Academic
arxiv.org·

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)

 💬LLMs  Content type: Academic
arxiv.org·

Zero and Few Shot Load Forecasting with Large Language Models

 🧠Deep Learning  Content type: Academic
arxiv.org·

Steganography Without Modification: Hidden Communication via LLM Seeds

 🔤Tokenization  Content type: Academic
arxiv.org··Hacker News

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