Natural Language Processing

Feeds to Scour
SubscribedAll
Scoured 132 posts in 9.2 ms

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

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

AI Chart Understanding Breakthrough: MIT-IBM Dataset Lets Small Models Beat GPT-4o

 ✍️Prompt Engineering
techtimes.com·

Measuring Embedding Drift: Why Hybrid Search Saves Stale Models.

 🎯Fine-Tuning
pub.towardsai.net
·

Meta-Attention: Teaching Models When Not to Answer

 🤖AI
hackernoon.com·

A Deep Dive into Calibration of Language Models: Platt Scaling, Isotonic Regression, Temperature Scaling

 🎛️Fine-tuning
kdnuggets.com·

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

 🎯RLHF  Content type: Academic
arxiv.org·

LangChain Series #2: Models Explained — LLMs, Chat Models, and Embeddings with Practical…

 🤖AI
pub.towardsai.net
·

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

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

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

 💬LLMs  Content type: Academic
arxiv.org·

Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting

 🤖AI  Content type: Academic
arxiv.org·

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

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

Dynamic Linear Attention

 🤖AI  Content type: Academic
arxiv.org·

A Regret Minimization Framework on Preference Learning in Large Language Models

 🎯RLHF  Content type: Academic
arxiv.org·

ACAT: A Collaborative Platform for Efficient Aspect-Based Sentiment Dataset Annotation

 📝NLP  Content type: Academic
arxiv.org·

Towards Tight Bounds for Streaming Attention

 🤖AI  Content type: Academic
arxiv.org·

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

 📝NLP  Content type: Academic
arxiv.org·

AI-Driven Test Case Generation from Natural Language Requirements: A Survey of Techniques and Research Gaps

 📝NLP  Content type: Academic
arxiv.org·

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

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

Alignment Defends LLMs from Property Inference Attacks

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

BLM-SGAN: Bidirectional Language Modeling for Semantic-Spatial Text-to-Image Generation

 🎨Generative AI  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