US 12,111,751 B2
Debugging tool for code generation neural language models
Colin Bruce Clement, Seattle, WA (US); David Alberto Nader Palacio, Williamsburg, VA (US); Neelakantan Sundaresan, Bellevue, WA (US); Alexey Svyatkovskiy, Bellevue, WA (US); and Michele Tufano, Bellevue, WA (US)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC., Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC., Redmond, WA (US)
Filed on Dec. 15, 2022, as Appl. No. 18/082,366.
Claims priority of provisional application 63/408,288, filed on Sep. 20, 2022.
Prior Publication US 2024/0104001 A1, Mar. 28, 2024
Int. Cl. G06F 9/44 (2018.01); G06F 11/36 (2006.01)
CPC G06F 11/3636 (2013.01) 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
a memory that stores one or more programs that are configured to be executed by the one or more processors, the one or more programs including instructions to perform actions that:
obtain a source code snippet generated by a neural language model given an input sequence of source code, wherein the input sequence includes a plurality of input source code tokens, wherein the source code snippet includes a plurality of output source code tokens;
locate an error in the source code snippet generated by the neural language model, wherein the error is associated with a select token in the source code snippet;
generate a set of rationales for the select token in the source code snippet, wherein the set of rationales comprises a smallest subset of tokens of the input sequence of source code tokens that led to generation of the select token in the source code snippet generated by the neural language model; and
identify a source of the error in the source code snippet generated by the neural language model to at least one token of the set of rationales associated with the select token in the source code snippet.