{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/151345"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/151345","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Truthfulness in Large Language Models","abstract":"Large language models (LLMs) have been experiencing a rapid rise in utility, accessibility, and popularity, but there are still many areas in which they can improve. One such area for improvement is their truthfulness. We seek to improve the truthfulness of LLMs by probing their internal representations. We find that a linear probe on the last hidden layer representation is able to improve a model’s accuracy by reducing its confidence in incorrect answers. However, this probe is less effective at perturbing the model to change its behavior and driving the model towards correct answers.","abstract_html":"Large language models (LLMs) have been experiencing a rapid rise in utility, accessibility, and popularity, but there are still many areas in which they can improve. One such area for improvement is their truthfulness. We seek to improve the truthfulness of LLMs by probing their internal representations. We find that a linear probe on the last hidden layer representation is able to improve a model’s accuracy by reducing its confidence in incorrect answers. However, this probe is less effective at perturbing the model to change its behavior and driving the model towards correct answers.","abstract_has_math":false,"creators":["Liu, Kevin"],"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":["Andreas, Jacob","Hadfield-Menell, Dylan"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06","date_published":"2023-06","updated_at":"2026-07-22T22:21:19Z","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/1721.1/151345","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Andreas, Jacob","Hadfield-Menell, Dylan"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Liu, Kevin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-07-31T19:32:58Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-07-31T19:32:58Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06"]},{"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","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"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/1721.1/151345"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Large language models (LLMs) have been experiencing a rapid rise in utility, accessibility, and popularity, but there are still many areas in which they can improve. One such area for improvement is their truthfulness. We seek to improve the truthfulness of LLMs by probing their internal representations. We find that a linear probe on the last hidden layer representation is able to improve a model’s accuracy by reducing its confidence in incorrect answers. However, this probe is less effective at perturbing the model to change its behavior and driving the model towards correct answers."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Truthfulness in Large Language Models"]}]}],"canonical_facts":{"dc:contributor.advisor":["Andreas, Jacob","Hadfield-Menell, Dylan"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Liu, Kevin"],"dc:date.accessioned":["2023-07-31T19:32:58Z"],"dc:date.available":["2023-07-31T19:32:58Z"],"dc:date.issued":["2023-06"],"dc:description.abstract":["Large language models (LLMs) have been experiencing a rapid rise in utility, accessibility, and popularity, but there are still many areas in which they can improve. One such area for improvement is their truthfulness. We seek to improve the truthfulness of LLMs by probing their internal representations. We find that a linear probe on the last hidden layer representation is able to improve a model’s accuracy by reducing its confidence in incorrect answers. However, this probe is less effective at perturbing the model to change its behavior and driving the model towards correct answers."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/151345"],"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":["Truthfulness in Large Language Models"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:19Z"}