Merge pull request #357 from cvs-health/patch/v0.5.6

Patch release: `v0.5.6`

Author: dylanbouchard

README.md

@@ -34,14 +34,14 @@
   </a>
 </p>
 <p align="center">
-  <a href="https://arxiv.org/pdf/2507.06196">
-    <img src="https://img.shields.io/badge/JMLR-Published-blue?style=flat" alt="JMLR Publication">
+  <a href="https://www.jmlr.org/papers/v27/25-1557.html">
+    <img src="https://img.shields.io/badge/JMLR-Published-112467?style=flat&style=for-the-badge&logo=semantic-scholar&logoColor=white" alt="JMLR Publication">
   </a>
   <a href="https://openreview.net/pdf?id=WOFspd4lq5">
-    <img src="https://img.shields.io/badge/TMLR-Published-blue?style=flat" alt="TMLR Publication">
+    <img src="https://img.shields.io/badge/TMLR-Published-4FA1CA?style=flat&logo=semantic-scholar&logoColor=white" alt="TMLR Publication">
   </a>
   <a href="https://arxiv.org/abs/2602.17431">
-    <img src="https://img.shields.io/badge/arXiv-2602.17431-B31B1B.svg" alt="arXiv">
+    <img src="https://img.shields.io/badge/arXiv-LongTextUQ-B31B1B?logo=arXiv&logoColor=white" alt="arXiv">
   </a>
 </p>
 
@@ -358,14 +358,15 @@ note={}
 The `uqlm` software package is described in this **[this paper](https://arxiv.org/abs/2507.06196)**, published in the **Journal of Machine Learning Research (JMLR)**. If you use the software, please cite:
 
 ```bibtex
-@misc{bouchard2025uqlmpythonpackageuncertainty,
-      title={UQLM: A Python Package for Uncertainty Quantification in Large Language Models}, 
-      author={Dylan Bouchard and Mohit Singh Chauhan and David Skarbrevik and Ho-Kyeong Ra and Viren Bajaj and Zeya Ahmad},
-      year={2025},
-      eprint={2507.06196},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2507.06196}, 
+@article{JMLR:v27:25-1557,
+  author  = {Dylan Bouchard and Mohit Singh Chauhan and David Skarbrevik and Ho-Kyeong Ra and Viren Bajaj and Zeya Ahmad},
+  title   = {UQLM: A Python Package for Uncertainty Quantification in Large Language Models},
+  journal = {Journal of Machine Learning Research},
+  year    = {2026},
+  volume  = {27},
+  number  = {13},
+  pages   = {1--10},
+  url     = {http://jmlr.org/papers/v27/25-1557.html}
 }
 ```
 

assets/README_PYPI.md

@@ -31,17 +31,18 @@
   </a>
 </p>
 <p align="center">
-  <a href="https://arxiv.org/pdf/2507.06196">
-    <img src="https://img.shields.io/badge/JMLR-Published-blue?style=flat" alt="JMLR Publication">
+  <a href="https://www.jmlr.org/papers/v27/25-1557.html">
+    <img src="https://img.shields.io/badge/JMLR-Published-112467?style=flat&style=for-the-badge&logo=semantic-scholar&logoColor=white" alt="JMLR Publication">
   </a>
   <a href="https://openreview.net/pdf?id=WOFspd4lq5">
-    <img src="https://img.shields.io/badge/TMLR-Published-blue?style=flat" alt="TMLR Publication">
+    <img src="https://img.shields.io/badge/TMLR-Published-4FA1CA?style=flat&logo=semantic-scholar&logoColor=white" alt="TMLR Publication">
   </a>
   <a href="https://arxiv.org/abs/2602.17431">
-    <img src="https://img.shields.io/badge/arXiv-2602.17431-B31B1B.svg" alt="arXiv">
+    <img src="https://img.shields.io/badge/arXiv-LongTextUQ-B31B1B?logo=arXiv&logoColor=white" alt="arXiv">
   </a>
 </p>
 
+
 UQLM is a Python library for Large Language Model (LLM) hallucination detection using state-of-the-art uncertainty quantification techniques. 
 
 ## Installation
@@ -312,30 +313,45 @@ The examples directory contains tutorials for:
 Each notebook includes detailed explanations and code samples that you can adapt to your specific use case.
 
 ## Citation
-A technical description of the `uqlm` scorers and extensive experimental results are presented in **[this paper](https://arxiv.org/abs/2504.19254)**. If you use our framework or toolkit, please cite:
+A technical description of the `uqlm` scorers and extensive experimental results are presented in **[this paper](https://openreview.net/pdf?id=WOFspd4lq5)**, published in **Transactions on Machine Learning Research (TMLR)**. If you use our framework or toolkit, please cite:
 
 ```bibtex
-@misc{bouchard2025uncertaintyquantificationlanguagemodels,
-      title={Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers}, 
-      author={Dylan Bouchard and Mohit Singh Chauhan},
-      year={2025},
-      eprint={2504.19254},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2504.19254}, 
+@article{
+bouchard2025uncertainty,
+title={Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, {LLM} Judge, and Ensemble Scorers},
+author={Dylan Bouchard and Mohit Singh Chauhan},
+journal={Transactions on Machine Learning Research},
+issn={2835-8856},
+year={2025},
+url={https://openreview.net/forum?id=WOFspd4lq5},
+note={}
 }
 ```
 
-The `uqlm` software package is described in this **[this paper](https://arxiv.org/abs/2507.06196)**. If you use the software, please cite:
+The `uqlm` software package is described in this **[this paper](https://arxiv.org/abs/2507.06196)**, published in the **Journal of Machine Learning Research (JMLR)**. If you use the software, please cite:
+
+```bibtex
+@article{JMLR:v27:25-1557,
+  author  = {Dylan Bouchard and Mohit Singh Chauhan and David Skarbrevik and Ho-Kyeong Ra and Viren Bajaj and Zeya Ahmad},
+  title   = {UQLM: A Python Package for Uncertainty Quantification in Large Language Models},
+  journal = {Journal of Machine Learning Research},
+  year    = {2026},
+  volume  = {27},
+  number  = {13},
+  pages   = {1--10},
+  url     = {http://jmlr.org/papers/v27/25-1557.html}
+}
+```
 
+The long-text methods and experiment results are described in **this paper**, available as a preprint on arXiv. To cite:
 ```bibtex
-@misc{bouchard2025uqlmpythonpackageuncertainty,
-      title={UQLM: A Python Package for Uncertainty Quantification in Large Language Models}, 
-      author={Dylan Bouchard and Mohit Singh Chauhan and David Skarbrevik and Ho-Kyeong Ra and Viren Bajaj and Zeya Ahmad},
-      year={2025},
-      eprint={2507.06196},
+@misc{bouchard2026finegraineduncertaintyquantificationlongform,
+      title={Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study}, 
+      author={Dylan Bouchard and Mohit Singh Chauhan and Viren Bajaj and David Skarbrevik},
+      year={2026},
+      eprint={2602.17431},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2507.06196}, 
+      url={https://arxiv.org/abs/2602.17431}, 
 }
 ```

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "uqlm"
-version = "0.5.5"
+version = "0.5.6"
 description = "UQLM (Uncertainty Quantification for Language Models) is a Python package for UQ-based LLM hallucination detection."
 readme = "assets/README_PYPI.md"
 license = "Apache-2.0"
@@ -39,7 +39,7 @@ dependencies = [
     "pandas>=2.3.0,<3.0.0",
     "sentence-transformers>=3.4,<6.0",
     "datasets>=3.3.2,<5.0.0",
-    "rich>=13.8.0,<14.0.0",
+    "rich>=13.8.0,<15.0.0",
     "ipywidgets>=8.1.7,<9.0.0",
 ]
 
@@ -62,16 +62,16 @@ docs = [
     "pydata_sphinx_theme==0.16.1",
     "sphinxcontrib-bibtex==2.6.3",
     "sphinx-autodoc-typehints==2.3.0",
-    "sphinx-gallery==0.18.0",
+    "sphinx-gallery==0.20.0",
     "sphinx-favicon==1.0.1",
-    "nbsphinx==0.9.6",
+    "nbsphinx==0.9.8",
 ]
 test = [
     "ipykernel>=6.29.5,<7.0.0",
     "langchain-openai>=0.2.6",
     "pytest>=8.3.5,<9.0.0",
     "langchain-google-vertexai>=2.0.8",
-    "pytest-asyncio>=0.25.3,<1.2.0",
+    "pytest-asyncio>=0.25.3,<1.4.0",
     "pytest-cov>=6,<8",
     "pytest-rerunfailures>=16.0,<17.0",
 ]