Robust and Fine-Grained Detection of AI Generated Texts
Paper
•
2504.11952
•
Published
•
11
LangChainDatasets
community
AI & ML interests
None defined yet.
Recent Activity
LangChainDatasets's activity
1024m
authored
a
paper
6 days ago
1024m
authored
a
paper
8 days ago
ImranzamanML
posted
an
update
8 days ago
Post
3582
Mental Health Chatbot by Fine-Tuning Llama 4
https://huggingface.co/blog/ImranzamanML/llama-4-fine-tuning-with-mental-health-counseling
https://huggingface.co/blog/ImranzamanML/llama-4-fine-tuning-with-mental-health-counseling
-
- 4 replies
1024m
authored
a
paper
13 days ago
ImranzamanML
posted
an
update
17 days ago
Post
1563
Llama 4 is here and it's making serious waves!
After diving into the latest benchmark results, it’s clear that Meta’s new Llama 4 lineup (Maverick, Scout, and Behemoth) is no joke.
Here are a few standout highlights🔍:
Llama 4 Maverick hits the sweet spot between cost and performance
- Outperforms GPT-4o in image tasks like ChartQA (90.0 vs 85.7) and DocVQA (94.4 vs 92.8)
- Beats others in MathVista and MMLU Pro too and at a fraction of the cost ($0.19–$0.49 vs $4.38 🤯)
Llama 4 Scout is lean, cost-efficient, and surprisingly capable
- Strong performance across image and language tasks (e.g. ChartQA: 88.8, DocVQA: 94.4)
- More affordable than most competitors and still beats out larger models like Gemini 2.0 Flash-Lite
Llama 4 Behemoth is the heavy hitter.
- Tops the charts in LiveCodeBench (49.4), MATH-500 (95.0), and MMLU Pro (82.2)
- Even edges out Claude 3 Sonnet and Gemini 2 Pro in multiple areas
Meta didn’t just show up, they delivered across multimodal, coding, reasoning, and multilingual benchmarks.
And honestly? Seeing this level of performance, especially at lower inference costs, is a big deal for anyone building on LLMs.
Curious to see how these models do in real-world apps next.
#AI #Meta #Llama4 #LLMs #Benchmarking #MachineLearning #OpenSourceAI #GenerativeAI
- 1 reply
Post
1359
🙋🏻♂️Hey there folks,
Did you know that you can use ModernBERT to detect model hallucinations ?
Check out the Demo : Tonic/hallucination-test
See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard
check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1
and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect
👆🏻if you like this topic please contribute code upstream 🚀
Did you know that you can use ModernBERT to detect model hallucinations ?
Check out the Demo : Tonic/hallucination-test
See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard
check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1
and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect
👆🏻if you like this topic please contribute code upstream 🚀
- 2 replies
Post
768
Powered by
KRLabsOrg/lettucedect-large-modernbert-en-v1 from KRLabsOrg.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](
KRLabsOrg
)
- **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](
KRLabsOrg
) - **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
ImranzamanML
posted
an
update
2 months ago
Post
3259
Hugging Face just launched the AI Agents Course – a free journey from beginner to expert in AI agents!
- Learn AI Agent fundamentals, use cases and frameworks
- Use top libraries like LangChain & LlamaIndex
- Compete in challenges & earn a certificate
- Hands-on projects & real-world applications
https://huggingface.co/learn/agents-course/unit0/introduction
You can join for a live Q&A on Feb 12 at 5PM CET to learn more about the course here
https://www.youtube.com/live/PopqUt3MGyQ
- Learn AI Agent fundamentals, use cases and frameworks
- Use top libraries like LangChain & LlamaIndex
- Compete in challenges & earn a certificate
- Hands-on projects & real-world applications
https://huggingface.co/learn/agents-course/unit0/introduction
You can join for a live Q&A on Feb 12 at 5PM CET to learn more about the course here
https://www.youtube.com/live/PopqUt3MGyQ
Post
2402
🙋🏻♂️hey there folks ,
Goedel's Theorem Prover is now being demo'ed on huggingface : Tonic/Math
give it a try !
Goedel's Theorem Prover is now being demo'ed on huggingface : Tonic/Math
give it a try !
Post
2987
🙋🏻♂️ Hey there folks ,
our team made a game during the @mistral-game-jam and we're trying to win the community award !
try our game out and drop us a ❤️ like basically to vote for us !
Mistral-AI-Game-Jam/TextToSurvive
hope you like it !
our team made a game during the @mistral-game-jam and we're trying to win the community award !
try our game out and drop us a ❤️ like basically to vote for us !
Mistral-AI-Game-Jam/TextToSurvive
hope you like it !
Post
1912
🙋🏻♂️ Hey there folks ,
Facebook AI just released JASCO models that make music stems .
you can try it out here : Tonic/audiocraft
hope you like it
Facebook AI just released JASCO models that make music stems .
you can try it out here : Tonic/audiocraft
hope you like it
Post
2475
🙋🏻♂️Hey there folks , Open LLM Europe just released Lucie 7B-Instruct model , a billingual instruct model trained on open data ! You can check out my unofficial demo here while we wait for the official inference api from the group :
Tonic/Lucie-7B hope you like it 🚀
valeriaWong
authored
2
papers
4 months ago
ImranzamanML
posted
an
update
5 months ago
Post
701
Deep understanding of (C-index) evaluation measure for better model
Lets start with three patients groups:
Group A
Group B
Group C
For each patient, we will predict risk score (higher score means higher risk of early event).
Step 1: Understanding Concordance Index
The Concordance Index (C-index) evaluate that how well the model ranks survival times.
Understand with sample data:
Group A has 3 patients with actual survival times and predicted risk scores:
Patient Actual Survival Time Predicted Risk Score
P1 5 months 0.8
P2 3 months 0.9
P3 10 months 0.2
Comparable pairs:
(P1, P2): P2 has a shorter survival time and a higher risk score → Concordant ✅
(P1, P3): P3 has a longer survival time and a lower risk score → Concordant ✅
(P2, P3): P3 has a longer survival time and a lower risk score → Concordant ✅
Total pairs = 3
Total concordant pairs = 3
C-index for Group A = Concordant pairs/Total pairs= 3/3 = 1.0
Step 2: Calculate C-index for All Groups
Repeat the process for all groups. For now we can assume:
Group A: C-index = 1.0
Group B: C-index = 0.8
Group C: C-index = 0.6
Step 3: Stratified Concordance Index
The Stratified Concordance Index combines the C-index scores of all groups and focusing on the following:
Average performance across groups (mean of C-indices).
Consistency across groups (low standard deviation of C-indices).
Formula:
Stratified C-index = Mean(C-index scores) - Standard Deviation(C-index scores)
Calculate the mean:
Mean=1.0 + 0.8 + 0.6/3 = 0.8
Calculate the standard deviation:
Standard Deviation= sqrt((1.0-0.8)^2 + (0.8-0.8)^2 + (0.6-0.8)^/3) = 0.16
Stratified C-index:
Stratified C-index = 0.8 - 0.16 = 0.64
Step 4: Interpret the Results
A high Stratified C-index means:
The model predicts well overall (high mean C-index).
Lets start with three patients groups:
Group A
Group B
Group C
For each patient, we will predict risk score (higher score means higher risk of early event).
Step 1: Understanding Concordance Index
The Concordance Index (C-index) evaluate that how well the model ranks survival times.
Understand with sample data:
Group A has 3 patients with actual survival times and predicted risk scores:
Patient Actual Survival Time Predicted Risk Score
P1 5 months 0.8
P2 3 months 0.9
P3 10 months 0.2
Comparable pairs:
(P1, P2): P2 has a shorter survival time and a higher risk score → Concordant ✅
(P1, P3): P3 has a longer survival time and a lower risk score → Concordant ✅
(P2, P3): P3 has a longer survival time and a lower risk score → Concordant ✅
Total pairs = 3
Total concordant pairs = 3
C-index for Group A = Concordant pairs/Total pairs= 3/3 = 1.0
Step 2: Calculate C-index for All Groups
Repeat the process for all groups. For now we can assume:
Group A: C-index = 1.0
Group B: C-index = 0.8
Group C: C-index = 0.6
Step 3: Stratified Concordance Index
The Stratified Concordance Index combines the C-index scores of all groups and focusing on the following:
Average performance across groups (mean of C-indices).
Consistency across groups (low standard deviation of C-indices).
Formula:
Stratified C-index = Mean(C-index scores) - Standard Deviation(C-index scores)
Calculate the mean:
Mean=1.0 + 0.8 + 0.6/3 = 0.8
Calculate the standard deviation:
Standard Deviation= sqrt((1.0-0.8)^2 + (0.8-0.8)^2 + (0.6-0.8)^/3) = 0.16
Stratified C-index:
Stratified C-index = 0.8 - 0.16 = 0.64
Step 4: Interpret the Results
A high Stratified C-index means:
The model predicts well overall (high mean C-index).
Post
3603
🙋🏻♂️hey there folks,
periodic reminder : if you are experiencing ⚠️500 errors ⚠️ or ⚠️ abnormal
we have a thread 👉🏻 https://discord.com/channels/879548962464493619/1295847667515129877
if you can record the problem and share it there , or on the forums in your own post , please dont be shy because i'm not sure but i do think it helps 🤗🤗🤗
periodic reminder : if you are experiencing ⚠️500 errors ⚠️ or ⚠️ abnormal
spaces behavior on load or launch ⚠️we have a thread 👉🏻 https://discord.com/channels/879548962464493619/1295847667515129877
if you can record the problem and share it there , or on the forums in your own post , please dont be shy because i'm not sure but i do think it helps 🤗🤗🤗
- 2 replies
Alignment-Lab-AI
posted
an
update
6 months ago
Post
1396
remember boys and girls, always keep all your data, its never a waste of time!
Post
1191
boomers still pick zenodo.org instead of huggingface ??? absolutely clownish nonsense , my random datasets have 30x more downloads and views than front page zenodos ... gonna write a comparison blog , but yeah... cringe.
-
- 1 reply
ImranzamanML
posted
an
update
6 months ago
Post
734
Easy steps for an effective RAG pipeline with LLM models!
1. Document Embedding & Indexing
We can start with the use of embedding models to vectorize documents, store them in vector databases (Elasticsearch, Pinecone, Weaviate) for efficient retrieval.
2. Smart Querying
Then we can generate query embeddings, retrieve top-K relevant chunks and can apply hybrid search if needed for better precision.
3. Context Management
We can concatenate retrieved chunks, optimize chunk order and keep within token limits to preserve response coherence.
4. Prompt Engineering
Then we can instruct the LLM to leverage retrieved context, using clear instructions to prioritize the provided information.
5. Post-Processing
Finally we can implement response verification, fact-checking and integrate feedback loops to refine the responses.
Happy to connect :)
1. Document Embedding & Indexing
We can start with the use of embedding models to vectorize documents, store them in vector databases (Elasticsearch, Pinecone, Weaviate) for efficient retrieval.
2. Smart Querying
Then we can generate query embeddings, retrieve top-K relevant chunks and can apply hybrid search if needed for better precision.
3. Context Management
We can concatenate retrieved chunks, optimize chunk order and keep within token limits to preserve response coherence.
4. Prompt Engineering
Then we can instruct the LLM to leverage retrieved context, using clear instructions to prioritize the provided information.
5. Post-Processing
Finally we can implement response verification, fact-checking and integrate feedback loops to refine the responses.
Happy to connect :)