starting documentation
diff --git a/unsupported/Eigen/AutoDiff b/unsupported/Eigen/AutoDiff
index 2bf8de6..c6f6ba0 100644
--- a/unsupported/Eigen/AutoDiff
+++ b/unsupported/Eigen/AutoDiff
@@ -35,6 +35,9 @@
   * This module features forward automatic differentation via a simple
   * templated scalar type wrapper AutoDiffScalar.
   *
+  * Warning : this should NOT be confused with numerical differentiation, which
+  * is a different method and has its own module in Eigen.
+  *
   * \code
   * #include <unsupported/Eigen/AutoDiff>
   * \endcode
diff --git a/unsupported/Eigen/NonLinear b/unsupported/Eigen/NonLinear
index 334b6d6..d4f18f0 100644
--- a/unsupported/Eigen/NonLinear
+++ b/unsupported/Eigen/NonLinear
@@ -31,8 +31,7 @@
 namespace Eigen {
 
 /** \ingroup Unsupported_modules
-  * \defgroup NonLinear Support for non linear optimization and non linear least
-  * square using minpack routines.
+  * \defgroup NonLinearOptimization_Module Non linear optimization module
   *
   * \code
   * #include <unsupported/Eigen/NonLinear>
diff --git a/unsupported/Eigen/NumericalDiff b/unsupported/Eigen/NumericalDiff
index 991ce7c..82a070d 100644
--- a/unsupported/Eigen/NumericalDiff
+++ b/unsupported/Eigen/NumericalDiff
@@ -30,9 +30,12 @@
 namespace Eigen {
 
 /** \ingroup Unsupported_modules
-  * \defgroup NumericalDiff_Module Support for numerical differenciation.
+  * \defgroup NumericalDiff_Module Numerical differenciation module
   * See http://en.wikipedia.org/wiki/Numerical_differentiation
   *
+  * Warning : this should NOT be confused with automatic differentiation, which
+  * is a different method and has its own module in Eigen.
+  *
   * \code
   * #include <unsupported/Eigen/NumericalDiff>
   * \endcode
diff --git a/unsupported/Eigen/src/NonLinear/LevenbergMarquardt.h b/unsupported/Eigen/src/NonLinear/LevenbergMarquardt.h
index f541c38..27c6a5f 100644
--- a/unsupported/Eigen/src/NonLinear/LevenbergMarquardt.h
+++ b/unsupported/Eigen/src/NonLinear/LevenbergMarquardt.h
@@ -1,4 +1,12 @@
 
+
+/**
+  * \brief Performs non linear optimization over a non-linear function,
+  * using a variant of the Levenberg Marquardt algorithm.
+  *
+  * Check wikipedia for more information.
+  * http://en.wikipedia.org/wiki/Levenberg%E2%80%93Marquardt_algorithm
+  */
 template<typename FunctorType, typename Scalar=double>
 class LevenbergMarquardt 
 {