CR

Carolyn Rose

cs.CLcs.AIcs.SEcs.LG

On Valency

published · living versions

W_t6demzc7·v1 · currentpublished

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

with Hyun Ryu, Jong-Heon Kim, Yiqing Xie, Seungone Kim +1

1 version

Preprints & journals

6 papers in the corpus · 2025–2026

Steer, Don't Solve: Training Small Critic Models for Large Code Agents2606.21811v2 · Shubham Gandhi, Yiqing Xie, Atharva Naik et al.2026 · 0 citationsarXiv

ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis2605.05485v1 · Atharva Naik, Yash Mathur, Prakam et al.2026 · 0 citationsarXiv

Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations2604.27093v2 · Mingqian Zheng, Malia Morgan, Liwei Jiang et al.2026 · 0 citationsarXiv

Argument Reconstruction as Supervision for Critical Thinking in LLMs2603.17432v3 · Hyun Ryu, Gyouk Chu, Gregor Betz et al.2026 · 0 citationsarXiv

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics2505.23126v5 · Atharva Naik, Prakam, Yash Mathur et al.2025 · 0 citationsarXiv

RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing2503.07358v1 · Yiqing Xie, Alex Xie, Divyanshu Sheth et al.2025 · 1 citationarXiv

Career total: 14 works. 6 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.