MemChainAI/adaptive-sentiment-classifier
Text Classification
ā¢
Updated
ā¢
3
Asankhaya Sharma PRO
codelion
AI & ML interests
Creator of OptiLLM, OpenEvolve, Adaptive Classifier, and PTS. Pioneering a new category in AI infrastructure: inference-time compute for LLMs.
Recent Activity
liked
a model
1 day ago
MemChainAI/adaptive-sentiment-classifier
new activity
1 day ago
google/frames-benchmark:Official evaluation code?
updated
a model
2 days ago
codelion/gemma-3-1b-it-icm-sft-mlx-fp16
Organizations
liked
a
model
1 day ago
Official evaluation code?
š
1
3
#18 opened 10 days ago
by
xbkj
updated
a
model
2 days ago
published
a
model
2 days ago
liked
a
Space
2 days ago
updated
a
model
3 days ago
published
a
model
3 days ago
updated
a
model
3 days ago
published
a
model
3 days ago
liked
a
dataset
3 days ago
updated
a
dataset
3 days ago
published
a
dataset
3 days ago
liked
a
dataset
3 days ago
reacted to
their
post with š¤šš„
5 days ago
Post
2460
Adaptive Classifier: Dynamic Text Classification with Strategic Learning
New text classification system that learns continuously without catastrophic forgetting. Achieved 22.2% robustness improvement on adversarial datasets while maintaining clean data performance.
šÆ THE PROBLEM
Traditional classifiers require complete retraining when adding new classes. Expensive and time-consuming, especially with adversarial users trying to game the system.
š KEY INNOVATIONS
ā¢ Hybrid memory-neural architecture (prototype-based + neural adaptation)
ā¢ Strategic classification using game theory to predict and defend against manipulation
ā¢ Elastic Weight Consolidation prevents catastrophic forgetting
š RESULTS
Tested on AI-Secure/adv_glue dataset:
ā¢ Clean data: 80.0% ā 82.2% (+2.2%)
ā¢ Manipulated data: 60.0% ā 82.2% (+22.2%)
ā¢ Zero performance drop under adversarial attacks
š¬ APPLICATIONS
ā¢ Hallucination detection: 80.7% recall for RAG safety
ā¢ LLM routing: 26.6% cost optimization improvement
ā¢ Content moderation: Robust against gaming attempts
āļø USAGE
pip install adaptive-classifier
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier("bert-base-uncased")
classifier.add_examples(texts, labels)
predictions = classifier.predict("New text")
š RESOURCES
Blog: https://huggingface.co/blog/codelion/adaptive-classifier
Code: https://github.com/codelion/adaptive-classifier
Models:
adaptive-classifier
Available models: llm-hallucination-detector, llm-config-optimizer, llm-router
Works with any HuggingFace transformer. Fully open source and production-ready!
New text classification system that learns continuously without catastrophic forgetting. Achieved 22.2% robustness improvement on adversarial datasets while maintaining clean data performance.
šÆ THE PROBLEM
Traditional classifiers require complete retraining when adding new classes. Expensive and time-consuming, especially with adversarial users trying to game the system.
š KEY INNOVATIONS
ā¢ Hybrid memory-neural architecture (prototype-based + neural adaptation)
ā¢ Strategic classification using game theory to predict and defend against manipulation
ā¢ Elastic Weight Consolidation prevents catastrophic forgetting
š RESULTS
Tested on AI-Secure/adv_glue dataset:
ā¢ Clean data: 80.0% ā 82.2% (+2.2%)
ā¢ Manipulated data: 60.0% ā 82.2% (+22.2%)
ā¢ Zero performance drop under adversarial attacks
š¬ APPLICATIONS
ā¢ Hallucination detection: 80.7% recall for RAG safety
ā¢ LLM routing: 26.6% cost optimization improvement
ā¢ Content moderation: Robust against gaming attempts
āļø USAGE
pip install adaptive-classifier
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier("bert-base-uncased")
classifier.add_examples(texts, labels)
predictions = classifier.predict("New text")
š RESOURCES
Blog: https://huggingface.co/blog/codelion/adaptive-classifier
Code: https://github.com/codelion/adaptive-classifier
Models:
adaptive-classifier
Available models: llm-hallucination-detector, llm-config-optimizer, llm-router
Works with any HuggingFace transformer. Fully open source and production-ready!
posted
an
update
5 days ago
Post
2460
Adaptive Classifier: Dynamic Text Classification with Strategic Learning
New text classification system that learns continuously without catastrophic forgetting. Achieved 22.2% robustness improvement on adversarial datasets while maintaining clean data performance.
šÆ THE PROBLEM
Traditional classifiers require complete retraining when adding new classes. Expensive and time-consuming, especially with adversarial users trying to game the system.
š KEY INNOVATIONS
ā¢ Hybrid memory-neural architecture (prototype-based + neural adaptation)
ā¢ Strategic classification using game theory to predict and defend against manipulation
ā¢ Elastic Weight Consolidation prevents catastrophic forgetting
š RESULTS
Tested on AI-Secure/adv_glue dataset:
ā¢ Clean data: 80.0% ā 82.2% (+2.2%)
ā¢ Manipulated data: 60.0% ā 82.2% (+22.2%)
ā¢ Zero performance drop under adversarial attacks
š¬ APPLICATIONS
ā¢ Hallucination detection: 80.7% recall for RAG safety
ā¢ LLM routing: 26.6% cost optimization improvement
ā¢ Content moderation: Robust against gaming attempts
āļø USAGE
pip install adaptive-classifier
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier("bert-base-uncased")
classifier.add_examples(texts, labels)
predictions = classifier.predict("New text")
š RESOURCES
Blog: https://huggingface.co/blog/codelion/adaptive-classifier
Code: https://github.com/codelion/adaptive-classifier
Models:
adaptive-classifier
Available models: llm-hallucination-detector, llm-config-optimizer, llm-router
Works with any HuggingFace transformer. Fully open source and production-ready!
New text classification system that learns continuously without catastrophic forgetting. Achieved 22.2% robustness improvement on adversarial datasets while maintaining clean data performance.
šÆ THE PROBLEM
Traditional classifiers require complete retraining when adding new classes. Expensive and time-consuming, especially with adversarial users trying to game the system.
š KEY INNOVATIONS
ā¢ Hybrid memory-neural architecture (prototype-based + neural adaptation)
ā¢ Strategic classification using game theory to predict and defend against manipulation
ā¢ Elastic Weight Consolidation prevents catastrophic forgetting
š RESULTS
Tested on AI-Secure/adv_glue dataset:
ā¢ Clean data: 80.0% ā 82.2% (+2.2%)
ā¢ Manipulated data: 60.0% ā 82.2% (+22.2%)
ā¢ Zero performance drop under adversarial attacks
š¬ APPLICATIONS
ā¢ Hallucination detection: 80.7% recall for RAG safety
ā¢ LLM routing: 26.6% cost optimization improvement
ā¢ Content moderation: Robust against gaming attempts
āļø USAGE
pip install adaptive-classifier
from adaptive_classifier import AdaptiveClassifier
classifier = AdaptiveClassifier("bert-base-uncased")
classifier.add_examples(texts, labels)
predictions = classifier.predict("New text")
š RESOURCES
Blog: https://huggingface.co/blog/codelion/adaptive-classifier
Code: https://github.com/codelion/adaptive-classifier
Models:
adaptive-classifier
Available models: llm-hallucination-detector, llm-config-optimizer, llm-router
Works with any HuggingFace transformer. Fully open source and production-ready!
upvoted
an
article
6 days ago
Article
Adaptive Classifier: Dynamic Text Classification with Continuous Learning
By
ā¢
ā¢
11
published
an
article
6 days ago
Article
Adaptive Classifier: Dynamic Text Classification with Continuous Learning
By
ā¢
ā¢
11
commented
a
paper
6 days ago