

{"id":61,"date":"2021-10-29T01:29:31","date_gmt":"2021-10-29T05:29:31","guid":{"rendered":"https:\/\/sites.temple.edu\/sancharibiswas\/?page_id=61"},"modified":"2026-10-20T12:07:13","modified_gmt":"2026-10-20T16:07:13","slug":"home","status":"publish","type":"page","link":"https:\/\/sites.temple.edu\/sancharibiswas\/","title":{"rendered":"Home"},"content":{"rendered":"<div style=\"max-width:860px;margin:0 auto;line-height:1.6;color:#1c2430\">\n<p>  <!-- ===================== INTRO ===================== --><\/p>\n<div style=\"padding-bottom:28px;border-bottom:2px solid #1c2430\">\n    <img decoding=\"async\" src=\"https:\/\/sites.temple.edu\/sancharibiswas\/files\/2026\/03\/20240401_194535-1024x875.jpg\" alt=\"Sanchari Biswas\" style=\"float:left;width:228px;max-width:100%;height:auto;margin:4px 28px 12px 0;border:1px solid #dfe3e8\" \/><\/p>\n<p style=\"margin:0 0 2px;font-size:1.7rem;font-weight:700;line-height:1.2\">Sanchari Biswas<\/p>\n<p style=\"margin:0 0 16px;font-size:0.9rem;font-weight:600;color:#8a1538;letter-spacing:0.05em;text-transform:uppercase\">PhD Student &middot; Computer and Information Sciences &middot; Temple University<\/p>\n<p style=\"margin:0 0 14px\"><strong>Sanchari Biswas<\/strong> is a PhD student in Computer and Information Sciences at Temple University, where she is advised by <a href=\"https:\/\/chiutan.github.io\/\" target=\"_blank\" rel=\"noreferrer noopener\" style=\"color:#8a1538;text-decoration:none;border-bottom:1px solid #c9ced6\">Prof. Chiu C. Tan<\/a>. Her research focuses on understanding and improving the reliability of Large Language Models (LLMs). She studies how these systems generate information, why they sometimes produce hallucinations or inconsistencies, and how structured reasoning and evaluation frameworks can help make AI systems more trustworthy. Her work lies at the intersection of trustworthy AI, language model reasoning, and security-oriented evaluation of modern AI systems.<\/p>\n<p style=\"margin:0;padding:10px 14px;background:#f6f1f3;border-left:3px solid #8a1538;color:#3b4553\"><strong style=\"color:#8a1538\">Currently:<\/strong> Working on domain-specific hallucination benchmarks and evaluation metrics for LLM reliability.<\/p>\n<div style=\"clear:both\"><\/div>\n<\/p><\/div>\n<p>  <!-- ===================== RESEARCH INTERESTS ===================== --><\/p>\n<h2 style=\"margin:40px 0 4px;font-size:1.3rem;font-weight:700;letter-spacing:0.02em\">Research Interests<\/h2>\n<div style=\"border-top:2px solid #1c2430;margin:0 0 14px\"><\/div>\n<ul style=\"margin:0;padding-left:20px;color:#3b4553\">\n<li style=\"margin:0 0 6px\">Hallucination Detection and Mitigation in Large Language Models<\/li>\n<li style=\"margin:0 0 6px\">Trustworthy, Safe, and Reliable AI Systems<\/li>\n<li style=\"margin:0 0 6px\">Multilingual Robustness and Cross-Lingual Security<\/li>\n<li style=\"margin:0 0 6px\">Evaluation Frameworks Inspired by Formal Verification<\/li>\n<li style=\"margin:0\">Policy-aware and Guardrail-aware AI Reasoning<\/li>\n<\/ul>\n<p>  <!-- ===================== CURRENT FOCUS ===================== --><\/p>\n<h2 style=\"margin:40px 0 4px;font-size:1.3rem;font-weight:700;letter-spacing:0.02em\">Current Focus<\/h2>\n<div style=\"border-top:2px solid #1c2430;margin:0 0 14px\"><\/div>\n<div style=\"padding:4px 0 4px 16px;border-left:3px solid #8a1538\">\n<p style=\"margin:0;color:#3b4553\">Sanchari&#8217;s current research investigates systematic approaches to identifying and analyzing hallucinations produced by large language models across domains such as security, education, and healthcare. Her work explores structured intermediate reasoning representations, constraint-based verification techniques, and scalable benchmarking methods designed to evaluate whether model outputs remain consistent, reliable, and aligned with user intent and safety policies.<\/p>\n<\/p><\/div>\n<p>  <!-- ===================== NEWS ===================== --><\/p>\n<h2 style=\"margin:40px 0 4px;font-size:1.3rem;font-weight:700;letter-spacing:0.02em\">News<\/h2>\n<div style=\"border-top:2px solid #1c2430;margin:0 0 4px\"><\/div>\n<div style=\"padding:12px 0;border-bottom:1px solid #dfe3e8\">\n    <span style=\"min-width:84px;font-size:0.85rem;font-weight:700;color:#8a1538;letter-spacing:0.05em\">APR 2026<\/span><br \/>\n    <span style=\"color:#3b4553\">Served as Judge at Delaware Valley Science Fair<\/span>\n  <\/div>\n<div style=\"padding:12px 0;border-bottom:1px solid #dfe3e8\">\n    <span style=\"min-width:84px;font-size:0.85rem;font-weight:700;color:#8a1538;letter-spacing:0.05em\">MAR 2026<\/span><br \/>\n    <span style=\"color:#3b4553\">Invited Panelist, &ldquo;Future Forward: Advancements in AI&rdquo;<\/span>\n  <\/div>\n<div style=\"padding:12px 0;border-bottom:1px solid #dfe3e8\">\n    <span style=\"min-width:84px;font-size:0.85rem;font-weight:700;color:#8a1538;letter-spacing:0.05em\">FEB 2026<\/span><br \/>\n    <span style=\"color:#3b4553\">Paper accepted at HealthCom 2026<\/span>\n  <\/div>\n<p>  <!-- ===================== ABOUT ME ===================== --><\/p>\n<h2 style=\"margin:40px 0 4px;font-size:1.3rem;font-weight:700;letter-spacing:0.02em\">About Me<\/h2>\n<div style=\"border-top:2px solid #1c2430;margin:0 0 14px\"><\/div>\n<p style=\"margin:0 0 18px;color:#3b4553\">Outside of research, Sanchari enjoys exploring creativity in different forms. She loves reading fiction, experimenting with cuisines from around the world, and discovering cultural connections through food. Cooking serves as both a creative outlet and a way to unwind after research. She is also passionate about music and enjoys singing Rabindrasangeet, finding it to be a grounding and reflective practice alongside the fast-paced world of academic research.<\/p>\n<div style=\"padding:10px;background:#f3f4f6;border:1px solid #dfe3e8\">\n    <img decoding=\"async\" src=\"https:\/\/sites.temple.edu\/sancharibiswas\/files\/2026\/04\/517200168_10227702388778346_6302618586020962663_n-519x1024.jpg\" alt=\"\" style=\"width:18.4%;height:auto;vertical-align:top;margin:0 1% 0 0\" \/><img decoding=\"async\" src=\"https:\/\/sites.temple.edu\/sancharibiswas\/files\/2026\/04\/IMG_0505-683x1024.jpg\" alt=\"\" style=\"width:24.2%;height:auto;vertical-align:top;margin:0 1% 0 0\" \/><img decoding=\"async\" src=\"https:\/\/sites.temple.edu\/sancharibiswas\/files\/2026\/04\/653381217_10230350598461933_6351839069386171238_n-1024x682.jpg\" alt=\"\" style=\"width:54.9%;height:auto;vertical-align:top;margin:0\" \/>\n  <\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Sanchari Biswas PhD Student &middot; Computer and Information Sciences &middot; Temple University Sanchari Biswas is a PhD student in Computer and Information Sciences at Temple University, where she is advised by Prof. Chiu C. Tan. Her research focuses on understanding and improving the reliability of Large Language Models (LLMs). She studies how these systems generate [&hellip;]<\/p>\n","protected":false},"author":29048,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-61","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/pages\/61","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/users\/29048"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/comments?post=61"}],"version-history":[{"count":13,"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/pages\/61\/revisions"}],"predecessor-version":[{"id":247,"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/pages\/61\/revisions\/247"}],"wp:attachment":[{"href":"https:\/\/sites.temple.edu\/sancharibiswas\/wp-json\/wp\/v2\/media?parent=61"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}