15 citations · 20 across the 5 of their papers we have counts for
6 papers
SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces
Harshit Joshi, Priyank Shethia, Monica S. Lam
Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while seeking…
SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
Harshit Joshi, Priyank Shethia, Jadelynn Dao +1
Systematic reviews -- which requires comprehensive evidence collection and synthesis from large document corpora in response to targeted research questions -- are foundational in f…
Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets
Harshit Joshi, Shicheng Liu, James Chen +2
Large Language Models can carry out human-like conversations in diverse settings, responding to user requests for tasks and knowledge. However, existing conversational agents imple…
FLAME: A small language model for spreadsheet formulas
Harshit Joshi, Abishai Ebenezer, José Cambronero +5
Spreadsheets are a vital tool for end-user data management. Using large language models for formula authoring assistance in these environments can be difficult, as these models are…
Repair Is Nearly Generation: Multilingual Program Repair with LLMs
Harshit Joshi, José Cambronero, Sumit Gulwani +3
Most programmers make mistakes when writing code. Some of these mistakes are small and require few edits to the original program -- a class of errors recently termed last mile mist…
Neurosymbolic Repair for Low-Code Formula Languages
Rohan Bavishi, Harshit Joshi, José Pablo Cambronero Sánchez +5
Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-specific formula languages to carry out nontrivial tasks. Often users can write most of the…