Update README.md

Added a workstep to explore mechanisms by which fine-tuned LLMs look at semantic context, and whether this can be controlled in terms of specifying the window of before and after tokens

README.md

@@ -41,6 +41,8 @@ HTR for the same tokens with Page to Page congruence, and broadly line by line c
 
    * Ability to correct words according to their Parts of Speech
    * Ability to assess grammatical correctness of Early Modern English and Notarial Latin at phrase level
+   * Ability to correct words according to their semantic context (specifying the number of tokens before
+     and after a word in which to look for semantic context)
      
 4. Examine existing benchmarks for transcription accuracy and apply to fine-tuned models