{"paper":{"title":"Scalable Conversational Assessment: Chat-Based Exams with a Two-Agent LLM Pipeline","arxiv_id":"2611.17220","primary_cat":"cs.CY","submitted_at":"2026-11-12T18:16:37+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Oral exams are compelling because (1) students can be asked to provide their reasoning for an answer and (2) their interactive nature permits follow-up questions to resolve ambiguous answers.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.35,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.83,"id":"s1","own":false,"role":"background","text":"But oral exams scale poorly.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.13,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.16,"method":0.0,"result":0.0,"background":0.83,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":true,"role":"contribution","text":"In this paper, we present scalable conversational assessment, an LLM-based system that conducts interactive text-based conversations with students to assess their ability to make and support an argument.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.91,"main_claim_p":0.23,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.99,"interpretation":0.0}},{"i":3,"p":0.98,"id":"s3","own":true,"role":"method","text":"We use a two-agent architecture to separate concerns and reduce the likelihood that answers are leaked to the student: the interviewer interacts directly with the student, but only receives guidance about the next question to ask the student; the hidden evaluator knows the goals of the whole activity, tracks the student's progress using a rubric, and guides the interviewer on when to follow-up on the current question or proceed to the next question.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.91,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.24,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":4,"p":0.97,"id":"s4","own":true,"role":"method","text":"The system was first tested using a collection of simulated students with LLM personas of a particular ability level or adversarial tactic (e.g., answer-extractors, prompt-injectors, confident fabricators).","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":5,"p":0.62,"id":"s5","own":true,"role":"method","text":"A novel element of this evaluation was that it required the use of a fictional assessment topic to prevent personas that shouldn't have information from using knowledge present in the LLM's pre-training.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.62,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.38,"interpretation":0.0}},{"i":6,"p":0.72,"id":"s6","own":true,"role":"method","text":"The system was also deployed in a small, elective AI literacy course in both formative and summative contexts.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.17,"role_probabilities":{"gap":0.0,"method":0.72,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.28,"interpretation":0.0}},{"i":7,"p":0.45,"id":"s7","own":true,"role":"result","text":"Through manual and post-facto AI review of the transcripts we identified opportunities to improve the follow-up question generation and ensure that grading only credited ideas that the student (and not the interviewer) contributed.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.97,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.19,"result":0.45,"background":0.0,"limitation":0.06,"future_work":0.21,"contribution":0.06,"interpretation":0.03}}]},"compiled":{"main_claim":{"p":0.69,"text":"In this paper, we present scalable conversational assessment, an LLM-based system that conducts interactive text-based conversations with students to assess their ability to make and support an argument.","location":"abstract s2","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6380,"cost_usd_reported":0.0},"compiled_at":"2026-11-14","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.09,"states_limitation":0.77,"human_participants":0.88,"controlled_comparison":0.05,"randomized_assignment":0.02,"states_quantitative_result":0.04,"compares_with_prior_results":0.1,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.92,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.92,"simulation_or_computation":0.08}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.52,"text":"A novel element of this evaluation was that it required the use of a fictional assessment topic to prevent personas that shouldn't have information from using knowledge present in the LLM's pre-training.","location":"abstract s5"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":8,"sentences_in_abstract":8},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}