Ashutosh Adhikari
@yourstrulyash.bsky.social
PhD student UofEdinurgh.
RQ3: Where do debate or consultancy fail?
Our analysis show that judges benefit when the experts are arguing for diverse opinions!
Red quadrant is when the judge is persuaded more often than they should (i.e. they are deceptive).
Our analysis show that judges benefit when the experts are arguing for diverse opinions!
Red quadrant is when the judge is persuaded more often than they should (i.e. they are deceptive).
November 1, 2025 at 7:30 PM
RQ3: Where do debate or consultancy fail?
Our analysis show that judges benefit when the experts are arguing for diverse opinions!
Red quadrant is when the judge is persuaded more often than they should (i.e. they are deceptive).
Our analysis show that judges benefit when the experts are arguing for diverse opinions!
Red quadrant is when the judge is persuaded more often than they should (i.e. they are deceptive).
RQ2: Can debate be used as a reliable mechanism for yielding quality reasoning data?
Yes! We show that the reasoning data attained from debate in a completely unsupervised manner imbue reasoning in the expert vision language models.
Yes! We show that the reasoning data attained from debate in a completely unsupervised manner imbue reasoning in the expert vision language models.
November 1, 2025 at 7:30 PM
RQ2: Can debate be used as a reliable mechanism for yielding quality reasoning data?
Yes! We show that the reasoning data attained from debate in a completely unsupervised manner imbue reasoning in the expert vision language models.
Yes! We show that the reasoning data attained from debate in a completely unsupervised manner imbue reasoning in the expert vision language models.
Excited to share my first work as a PhD student at EdinburghNLP that I will be presenting at EMNLP!
RQ1: Can we achieve scalable oversight across modalities via debate?
Yes! We show that debating VLMs lead to better model quality of answers for reasoning tasks.
RQ1: Can we achieve scalable oversight across modalities via debate?
Yes! We show that debating VLMs lead to better model quality of answers for reasoning tasks.
November 1, 2025 at 7:30 PM
Excited to share my first work as a PhD student at EdinburghNLP that I will be presenting at EMNLP!
RQ1: Can we achieve scalable oversight across modalities via debate?
Yes! We show that debating VLMs lead to better model quality of answers for reasoning tasks.
RQ1: Can we achieve scalable oversight across modalities via debate?
Yes! We show that debating VLMs lead to better model quality of answers for reasoning tasks.