{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/162553"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/162553","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Discovering and Detecting Tax Avoidance Using Natural Language Processing and Coevolutionary Algorithms","abstract":"The Internal Revenue Service estimates that unpaid taxes cost the United States up to $1 trillion each year, much of it through tax avoidance schemes such as the Installment Bogus Optional Basis strategy (iBOB). This thesis focuses on discovering and detecting iBOB schemes within a tax network by using a coevolutionary framework powered by two large language model (LLM) agents: a tax planner, which generates transactions to reduce tax and suspicion, and an auditor, which generates patterns to detect tax avoidance. This thesis shows that as the tax planner and auditor evolve against each other, the planner consistently uncovers iBOB transactions and even discovers more effective variants than those previously known. In turn, the auditor learns to generate increasingly targeted detection patterns that adapt to the planner’s changing strategies. Their interaction leads to oscillating behavior between avoidance and enforcement, providing a new LLM-based framework for studying the dynamics of tax compliance.","abstract_html":"The Internal Revenue Service estimates that unpaid taxes cost the United States up to $1 trillion each year, much of it through tax avoidance schemes such as the Installment Bogus Optional Basis strategy (iBOB). This thesis focuses on discovering and detecting iBOB schemes within a tax network by using a coevolutionary framework powered by two large language model (LLM) agents: a tax planner, which generates transactions to reduce tax and suspicion, and an auditor, which generates patterns to detect tax avoidance. This thesis shows that as the tax planner and auditor evolve against each other, the planner consistently uncovers iBOB transactions and even discovers more effective variants than those previously known. In turn, the auditor learns to generate increasingly targeted detection patterns that adapt to the planner’s changing strategies. Their interaction leads to oscillating behavior between avoidance and enforcement, providing a new LLM-based framework for studying the dynamics of tax compliance.","abstract_has_math":false,"creators":["Bhattacharya, Joy Sera"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["O’Reilly, Una-May","Hemberg, Erik"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:21:10Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/162553","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["O’Reilly, Una-May","Hemberg, Erik"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Bhattacharya, Joy Sera"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-08-27T14:32:49Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-08-27T14:32:49Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/162553"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The Internal Revenue Service estimates that unpaid taxes cost the United States up to $1 trillion each year, much of it through tax avoidance schemes such as the Installment Bogus Optional Basis strategy (iBOB). This thesis focuses on discovering and detecting iBOB schemes within a tax network by using a coevolutionary framework powered by two large language model (LLM) agents: a tax planner, which generates transactions to reduce tax and suspicion, and an auditor, which generates patterns to detect tax avoidance. This thesis shows that as the tax planner and auditor evolve against each other, the planner consistently uncovers iBOB transactions and even discovers more effective variants than those previously known. In turn, the auditor learns to generate increasingly targeted detection patterns that adapt to the planner’s changing strategies. Their interaction leads to oscillating behavior between avoidance and enforcement, providing a new LLM-based framework for studying the dynamics of tax compliance."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["MNG"]},{"key":"dc:title","label":"Title","values":["Discovering and Detecting Tax Avoidance Using Natural Language Processing and Coevolutionary Algorithms"]}]}],"canonical_facts":{"dc:contributor.advisor":["O’Reilly, Una-May","Hemberg, Erik"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Bhattacharya, Joy Sera"],"dc:date.accessioned":["2025-08-27T14:32:49Z"],"dc:date.available":["2025-08-27T14:32:49Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["The Internal Revenue Service estimates that unpaid taxes cost the United States up to $1 trillion each year, much of it through tax avoidance schemes such as the Installment Bogus Optional Basis strategy (iBOB). This thesis focuses on discovering and detecting iBOB schemes within a tax network by using a coevolutionary framework powered by two large language model (LLM) agents: a tax planner, which generates transactions to reduce tax and suspicion, and an auditor, which generates patterns to detect tax avoidance. This thesis shows that as the tax planner and auditor evolve against each other, the planner consistently uncovers iBOB transactions and even discovers more effective variants than those previously known. In turn, the auditor learns to generate increasingly targeted detection patterns that adapt to the planner’s changing strategies. Their interaction leads to oscillating behavior between avoidance and enforcement, providing a new LLM-based framework for studying the dynamics of tax compliance."],"dc:description.degree":["MNG"],"dc:identifier.uri":["https://hdl.handle.net/1721.1/162553"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Discovering and Detecting Tax Avoidance Using Natural Language Processing and Coevolutionary Algorithms"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:10Z"}