alphaFeedback
CD
cs.AIcs.CLcs.SEcs.CRcs.LGcs.CVcs.IRcs.ITcs.PLmath.IT

On Valency

published · living versions
W_ebbegyeg·v1 · currentpublished
Post-Training Large Language Models with LLMON
with Basel Shbita, Michael Hind, Nathan Fulton, Shubhi Asthana +6
1 version

Preprints & journals

12 papers in the corpus · 2021–2026
ChartRevise: A Dataset and Evaluation Protocol for Exact Chart Editing via Code2609.38642v1 · Jiaxiang Tang, Yi Zhou, Chad DeLuca et al.2026 · 0 citationsarXiv
The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance2608.11694v1 · Shailja Thakur, Sungeun An, Chad DeLuca et al.2026 · 0 citationsarXiv
Runtime-Structured Task Decomposition for Agentic Coding Systems2605.15425v1 · Shubhi Asthana, Bing Zhang, Chad DeLuca et al.2026 · 0 citationsarXiv
A Systematic Approach for Large Language Models Debugging2604.23027v1 · Basel Shbita, Anna Lisa Gentile, Bing Zhang et al.2026 · 0 citationsarXiv
STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs2604.18177v2 · Sungeun An, Swanand Ravindra Kadhe, Shailja Thakur et al.2026 · 0 citationsarXiv
LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics2603.24929v2 · Farhan Ahmed, Yuya Jeremy Ong, Chad DeLuca2026 · 0 citationsarXiv
Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails2508.18384v1 · Kellen Tan Cheng, Anna Lisa Gentile, Chad DeLuca et al.2025 · 0 citationsarXiv
OneShield -- the Next Generation of LLM Guardrails2507.21170v2 · Chad DeLuca, Anna Lisa Gentile, Shubhi Asthana et al.2025 · 0 citationsarXiv
Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications2501.12456v1 · Shubhi Asthana, Bing Zhang, Ruchi Mahindru et al.2025 · 1 citationarXiv
SAUCE: Truncated Sparse Document Signature Bit-Vectors for Fast Web-Scale Corpus Expansion2108.11948v1 · Muntasir Wahed, Daniel Gruhl, Alfredo Alba et al.2021 · 0 citationsarXiv
Career total: 26 works. 12 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.