collaborators

10 papers

cs.CL2026

An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?

Abhinav Rao, Liancheng Gong, Bin Hu +1

Recent work has reported Emergent Misalignment (EM), where language models fine-tuned on narrow, domain-specific misaligned datasets abruptly acquire broadly misaligned behavior, a…

cs.SE2026

Steer, Don't Solve: Training Small Critic Models for Large Code Agents

Shubham Gandhi, Yiqing Xie, Atharva Naik +2

End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimizing code-level execution and s…

cs.CL2026

ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis

Atharva Naik, Yash Mathur, Prakam +2

LLMs can solve program synthesis tasks but remain inefficient and unreliable on hard instances requiring large combinatorial search. Given a small set of reasoning traces, we use c…

cs.SE2026

MetaLint: Easy-to-Hard Generalization for Code Linting

Atharva Naik, Lawanya Baghel, Dhakshin Govindarajan +4

Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during traini…

cs.CL2026

ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models

Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik +1

While Multimodal Large Language Models (MLLMs) perform strongly on single-turn chart generation, their ability to support real-world exploratory data analysis remains underexplored…

cs.CL2026

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics

Atharva Naik, Prakam, Yash Mathur +6

Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangling, few abstract away from doma…