I know how to prove
$$\sum_{k=1}^n \frac{(-1)^{k-1}}{k }\binom{n}{k}= H_n$$ by tackling it with the beta function.
I was actually wondering if there is a proof of this fact without using the property of the Beta function $$B(x,y) = \frac{\Gamma(x)\Gamma(y)}{\Gamma(x+y)}$$
Note: This can be found for instance as Example 3, section 1.2 in Combinatorial Identities by John Riordan.
Applying the Euler transform (1) to the left-hand side of the identity \begin{align*} \sum_{k=1}^n \frac{(-1)^{k-1}}{k }\binom{n}{k}= H_n \end{align*} we set $a_k=\frac{(-1)^{k-1}}{k}$ and obtain as generating function \begin{align*} A(z)=\sum_{k=1}^\infty \frac{(-1)^{k-1}}{k}z^k=\ln(1+z)\tag{2} \end{align*}
Note: A proof of the Euler transformation formula can be found e.g. in Harmonic Number Identities Via Euler's transform by K.N. Boyadzhiev.