8 papers
Scaling Competence, Shrinking Reasoning: Cognitive Signatures in Language Model Learning
Mukul Singh, Ananya Singha, Arjun Radhakrishna +1
We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the hum…
Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models
Mukul Singh, Ananya Singha, Aishni Parab +2
Associative thinking--the ability to connect seemingly unrelated ideas--is a foundational element of human creativity and problem-solving. This paper explores whether reinforcement…
Do Code Models Suffer from the Dunning-Kruger Effect?
Mukul Singh, Somya Chatterjee, Arjun Radhakrishna +1
As artificial intelligence systems increasingly collaborate with humans in creative and technical domains, questions arise about the cognitive boundaries and biases that shape our…
Collaboration and Conflict between Humans and Language Models through the Lens of Game Theory
Mukul Singh, Arjun Radhakrishna, Sumit Gulwani
Language models are increasingly deployed in interactive online environments, from personal chat assistants to domain-specific agents, raising questions about their cooperative and…
Tabularis Formatus: Predictive Formatting for Tables
Mukul Singh, José Cambronero, Sumit Gulwani +2
Spreadsheet manipulation software are widely used for data management and analysis of tabular data, yet the creation of conditional formatting (CF) rules remains a complex task req…
Diffusion is a code repair operator and generator
Mukul Singh, Gust Verbruggen, Vu Le +1
Code diffusion models generate code by iteratively removing noise from the latent representation of a code snippet. During later steps of the diffusion process, when the code snipp…