updated README

README.md

@@ -9,31 +9,52 @@ pipline_tag: text-classficiation
 
 <img src="https://huggingface.co/vectara/hallucination_evaluation_model/resolve/main/candle.png" width="50" height="50" style="display: inline;">  In Loving memory of Simon Mark Hughes...
 
-Click [here](https://huggingface.co/spaces/vectara/hhem-2.1-open-demo) for HHEM-2.1-Open demo app. 
+## Quickstart: try HHEM-2.1-Open Live Demo
 
-<iframe src="https://vectara-hhem-2-1-open-demo.hf.space/" title="Demo for HHEM-2.1-Open"></iframe>
+👉 **[Launch Interactive Demo](https://huggingface.co/spaces/vectara/hhem-2.1-open-demo)** - No setup required, runs in your browser
 
-With a performance superior than GPT-3.5-Turbo and GPT-4 but a footprint of less than 600MB RAM, 
-HHEM-2.1-Open is the lastest open source version of Vectara's HHEM series models for detecting hallucinations in LLMs. They are particularly useful in the context of building retrieval-augmented-generation (RAG) applications where a set of facts is summarized by an LLM, and HHEM can be used to measure the extent to which this summary is factually consistent with the facts.
+<iframe src="https://vectara-hhem-2-1-open-demo.hf.space/" title="Demo for HHEM-2.1-Open"></iframe>
 
-If you are interested to learn more about RAG or experiment with Vectara, you can [sign up](https://console.vectara.com/signup/?utm_source=huggingface&utm_medium=space&utm_term=hhem-model&utm_content=console&utm_campaign=) for a Vectara account.
+💡 **Quick test**: Try inputting "The capital of France is Berlin" as premise and "The capital of France is Paris" as hypothesis to see HHEM detect this factual but hallucinated case.
 
+HHEM-2.1-Open is the latest open source version of [Vectara](https://vectara.com)'s HHEM series models for detecting hallucinations in LLMs. These are particularly useful in the context of building retrieval-augmented-generation (RAG) applications or Agentic workflows, where a set of facts is summarized by an LLM, and HHEM can be used to measure the extent to which this summary is factually consistent with the facts.
 
 ## Hallucination Detection 101
-By "hallucinated" or "factually inconsistent", we mean that a text (hypothesis, to be judged) is not supported by another text (evidence/premise, given). You **always need two** pieces of text to determine whether a text is hallucinated or not. When applied to RAG (retrieval augmented generation), the LLM is provided with several pieces of text (often called facts or context) retrieved from some dataset, and a hallucination would indicate that the summary (hypothesis) is not supported by those facts (evidence). 
+By "hallucinated" or "factually inconsistent", we mean that a text (hypothesis, to be judged) is not supported by another text (evidence/premise, given). You **always need two** pieces of text to determine whether a text is hallucinated or not. When applied to RAG or AI Agents, the LLM is provided with several pieces of text (often called facts or context) retrieved from some dataset, and a hallucination would indicate that the summary (hypothesis) is not supported by those facts (evidence). 
 
-A common type of hallucination in RAG is **factual but hallucinated**. 
+A common type of RAG hallucination is **factual but hallucinated**. 
 For example, given the premise _"The capital of France is Berlin"_, the hypothesis _"The capital of France is Paris"_ is hallucinated -- although it is true in the world knowledge. This happens when LLMs do not generate content based on the textual data provided to them as part of the RAG retrieval process, but rather generate content based on their pre-trained knowledge.
 
 Additionally, hallucination detection is "asymmetric" or is not commutative. For example, the hypothesis _"I visited Iowa"_ is considered hallucinated given the premise _"I visited the United States"_, but the reverse is consistent.
 
-## Using HHEM-2.1-Open
+💡 **Using HHEM in production?** We'd love to hear about your use case! Connect with us on [LinkedIn](https://linkedin.com/company/vectara) or [Twitter](https://twitter.com/vectara).
+
+## AI Engineers: Stay Updated on Hallucination Mitigation
+
+Hallucinations mitigation is a growing field, that includes both hallucination detection and correction.
+Specifically:
+
+- **HHEM** is a specialized model for **detecting** hallucinations in LLM outputs - it identifies when generated text is not supported by the provided context in RAG.
+- **VHC (Vectara Hallucination Corrector)** can **correct** hallucinations - fix inaccurate generated content (for RAG or Agents), ensuring its consistent with the context. [Learn more about VHC](https://www.vectara.com/blog/vectaras-hallucination-corrector).
+
+Together, these tools provide a comprehensive approach to hallucination mitigation, helping you to create better and more reliable AI applications.
+
+**Want to learn more?** Here are some resources to learn more about hallucination mitigation and AI safety:
 
-> HHEM-2.1 has some breaking change from HHEM-1.0. Your code that works with HHEM-1 (November 2023) will not work anymore. While we are working on backward compatibility, please follow the new usage instructions below.
+1. 📧 **[Join our newsletter](https://21542831.hs-sites.com/vectara-community-newsletter-sign-up)** for up to date updates on hallucination mitigation.
+
+2. 🚀 **[Sign up for Vectara](https://console.vectara.com/signup/?utm_source=huggingface&utm_medium=space&utm_term=hhem-model&utm_content=console&utm_campaign=)** - Access Vectara Hallucination Corrector (VHC) and gain hands-on experience using RAG and Agent workflows with VHC.
+
+3. Join our community:
+- 🔗 **LinkedIn**: Follow [@Vectara](https://linkedin.com/company/vectara) for AI safety insights and industry updates
+- 🐦 **X/Twitter**: [@vectara](https://twitter.com/vectara) for real-time updates and research discussions  
+- ⭐ **GitHub**: [Star our hallucination leaderboard](https://github.com/vectara/hallucination-leaderboard) which tracks LLM hallucination rates across leading LLMs.
+
+## Using HHEM-2.1-Open
 
 Here we provide several ways to use HHEM-2.1-Open in the `transformers` library.
 
-> You may run into a warning message that "Token indices sequence length is longer than the specified maximum sequence length". Please ignore it which is inherited from the foundation, T5-base. 
+>   You may run into a warning message that "Token indices sequence length is longer than the specified maximum sequence length". Please ignore it which is inherited from the foundation, T5-base. 
 
 ### Using with `AutoModel` 
 
@@ -101,10 +122,20 @@ print(simple_scores)
 
 Of course, with `pipeline`, you can also get the most likely label, or the label with the highest score, by setting `top_k=1`. 
 
+## HHEM-2.3 and the LLM Hallucination Leaderboard
+
+**See how LLMs compare**: HHEM-2.3, our latest commercial hallucination detection model, powers our [live leaderboard](https://huggingface.co/spaces/vectara/leaderboard) that continuously benchmarks leading LLMs for hallucination rates. Watch comparisons of the latest models including GPT-5, Claude 4, Grok-4, Gemini 2.5, Llama4, Mistrak, DeepSeek, and many others.
+
+**HHEM-2.3 advantages over the open source version**:
+- Enhanced accuracy and performance
+- Cross-lingual support (English, German, French, Portuguese, Spanish, Arabic, Chinese-Simplified, Korean, Russian, Japanese, and Hindi) 
+- Available exclusively via Vectara's platform
+
+🔍 **Track AI safety across the industry**: The leaderboard updates regularly as new models are released, giving the community insights into which LLMs are most reliable for factual tasks. All data and methodology are [open source](https://github.com/vectara/hallucination-leaderboard).
 
 ## HHEM-2.1-Open vs. HHEM-1.0
 
-The major difference between HHEM-2.1-Open and the original HHEM-1.0 is that HHEM-2.1-Open has an unlimited context length, while HHEM-1.0 is capped at 512 tokens. The longer context length allows HHEM-2.1-Open to provide more accurate hallucination detection for RAG which often needs more than 512 tokens. 
+HHEM-1.0 is the first open version of HHEM. The major difference between HHEM-2.1-Open and the original HHEM-1.0 is that HHEM-2.1-Open has an unlimited context length, while HHEM-1.0 is capped at 512 tokens. The longer context length allows HHEM-2.1-Open to provide more accurate hallucination detection for RAG which often needs more than 512 tokens. 
 
 The tables below compare the two models on the [AggreFact](https://arxiv.org/pdf/2205.12854) and [RAGTruth](https://arxiv.org/abs/2401.00396) benchmarks, as well as GPT-3.5-Turbo and GPT-4. In particular, on AggreFact, we focus on its SOTA subset (denoted as `AggreFact-SOTA`) which contains summaries generated by Google's T5, Meta's BART, and Google's Pegasus, which are the three latest models in the AggreFact benchmark. The results on RAGTruth's summarization (denoted as `RAGTruth-Summ`) and QA (denoted as `RAGTruth-QA`) subsets are reported separately. The GPT-3.5-Turbo and GPT-4 versions are 01-25 and 06-13 respectively. The zero-shot results of the two GPT models were obtained using the prompt template in [this paper](https://arxiv.org/pdf/2303.15621).
 
@@ -148,23 +179,20 @@ Table 4: Percentage points of HHEM-2.1-Open's balanced accuracies over GPT-3.5-T
 
 Another advantage of HHEM-2.1-Open is its efficiency. HHEM-2.1-Open can be run on consumer-grade hardware, occupying less than 600MB RAM space at 32-bit precision and elapsing around 1.5 second for a 2k-token input on a modern x86 CPU.
 
-## HHEM-2.1: The more powerful, proprietary counterpart of HHEM-2.1-Open
-
-As you may have already sensed from the name, HHEM-2.1-Open is the open source version of the premium HHEM-2.1. HHEM-2.1 (without the `-Open`) is offered exclusively via Vectara's RAG-as-a-service platform. The major difference between HHEM-2.1 and HHEM-2.1-Open is that HHEM-2.1 is cross-lingual on three languages: English, German, and French, while HHEM-2.1-Open is English-only. "Cross-lingual" means any combination of the three languages, e.g., documents in German, query in English, results in French.
+## Hallucination detection with Vectara
 
-### Why RAG in Vectara? 
+Vectara provides a Trusted Generative AI platform. The platform allows organizations to rapidly create an AI agent experience which is grounded in the data, documents, and knowledge that they have. Vectara solves critical problems required for enterprise adoption of RAG and Agentic AI applications, namely: reduces hallucination, provides explainability / provenance, enforces access control, allows for real-time updatability of the knowledge, and mitigates intellectual property / bias concerns from large language models.
 
-Vectara provides a Trusted Generative AI platform. The platform allows organizations to rapidly create an AI assistant experience which is grounded in the data, documents, and knowledge that they have. Vectara's serverless RAG-as-a-Service also solves critical problems required for enterprise adoption, namely: reduces hallucination, provides explainability / provenance, enforces access control, allows for real-time updatability of the knowledge, and mitigates intellectual property / bias concerns from large language models.
+HHEM-2.3 is fully integrated into Vectara and is automtically returned with every query API call.
 
-To start benefiting from HHEM-2.1, you can [sign up](https://console.vectara.com/signup/?utm_source=huggingface&utm_medium=space&utm_term=hhem-model&utm_content=console&utm_campaign=) for a Vectara account, and you will get the HHEM-2.1 score returned with every query automatically.
+To start benefiting from HHEM-2.3, you can [sign up](https://console.vectara.com/signup/?utm_source=huggingface&utm_medium=space&utm_term=hhem-model&utm_content=console&utm_campaign=) for a Vectara account, and you will get the HHEM-2.3 score returned with every query automatically.
 
 Here are some additional resources:
 1. Vectara [API documentation](https://docs.vectara.com/docs).
-2. Quick start using Forrest's [`vektara` package](https://vektara.readthedocs.io/en/latest/crash_course.html).
-3. Learn more about Vectara's [Boomerang embedding model](https://vectara.com/blog/introducing-boomerang-vectaras-new-and-improved-retrieval-model/), [Slingshot reranker](https://vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages/), and [Mockingbird LLM](https://vectara.com/blog/mockingbird-a-rag-and-structured-output-focused-llm/)
+2. Vectara [SDK](https://github.com/vectara/python-sdk).
+3. Quick start using Forrest's [`vektara` package](https://vektara.readthedocs.io/en/latest/crash_course.html).
+4. Learn more about Vectara's [Boomerang embedding model](https://vectara.com/blog/introducing-boomerang-vectaras-new-and-improved-retrieval-model/), [Slingshot reranker](https://vectara.com/blog/deep-dive-into-vectara-multilingual-reranker-v1-state-of-the-art-reranker-across-100-languages/), and [Mockingbird LLM](https://vectara.com/blog/mockingbird-a-rag-and-structured-output-focused-llm/)
 
-## LLM Hallucination Leaderboard
-If you want to stay up to date with results of the latest tests using this model to evaluate the top LLM models, we have a [public leaderboard](https://huggingface.co/spaces/vectara/leaderboard) that is periodically updated, and results are also available on the [GitHub repository](https://github.com/vectara/hallucination-leaderboard).
 
 # Cite this model