[ Please register at https://sjsu.zoom.us/meeting/register/tZMlc-mspjItGNTBJ2LBC0aFKKw4bJIj1oC1 to attend via Zoom. You can anyway watch it live or anytime after the event on this YouTube channel: https://www.youtube.com/channel/UC4kaO4mrTxrCltxb0HalV3Q]
Large Language Models, despite their astounding reasoning abilities, are not faithful problem solvers. While their abilities are strongly correlated with scale, even humongous models like GPT-3.5 or GPT-4 can become inconsistent reasoners. Recent advances in verbose prompting techniques like chain-of-thought try to elicit step-by-step decomposition so that the model can solve a sequence of simpler problems to finally reach the goal. Augmenting external tools like web search or calculators has also been proposed to offload deterministic tasks. However, foundational language models learn neither problem decomposition nor tool usage. In this talk, the speaker will present potent solutions towards offloading reasoning subtasks in the case of mathematical problem solving: how to teach an auxiliary (and potentially frugal) language model to coordinate with black-box solvers, symbolic or language model-based, to successfully answer mathematical problems. This talk will focus on successfully teaching language models to perform reasoning from non-human feedback and how rewards beyond just the correctness of the final answer are essential for better learning.
Tanmoy Chakraborty is an associate professor of electrical engineering and an associate faculty member of the Yardi School of AI at IIT Delhi. He leads the Laboratory for Computational Social Systems (LCS2), a research group specializing in NLP and Computational Social Science. His current research primarily focuses on empowering frugal language models for improved reasoning, grounding, and prompting and applying them specifically to two applications — mental health counselling and Cyber-informatics. Tanmoy obtained his PhD in 2015 from IIT Kharagpur as a Google PhD scholar. Subsequently, he worked as a postdoctoral researcher at the University of Maryland, College Park and as a faculty member at IIIT Delhi. Tanmoy has received numerous awards, including the Ramanujan Fellowship, PAKDD Early Career Award, ACL’23 Outstanding Paper Award, IJCAI’23 AI for Good Award, and several faculty awards/gifts from many industries like Facebook, Google, LinkedIn, JP Morgan, and Adobe. He has authored a textbook on “Social Network Analysis”. More details may be found at tanmoychak.com
IEEE Computer Society, Silicon Valley Chapter