alphaFeedback
DB

Daniel M. Bikel

cs.CLcs.AIcs.LGcs.SDeess.AS

On Valency

published · living versions
W_uj7fk9jx·v1 · currentpublished
Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention
with Serdarcan Dilbaz, Arjun Krishna, Kiran Kamble
1 version

Preprints & journals

11 papers in the corpus · 2020–2026
Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models2606.10949v2 · Shelly Bensal, Axel Magnuson, Aparna Balagopalan et al.2026 · 0 citationsarXiv
Auditing LLM Benchmarks with Item Response Theory2605.30504v2 · Sander Land, Daniel M. Bikel2026 · 0 citationsarXiv
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens2604.26355v7 · Zhenyu Zhao, Sander Land, Daniel M. Bikel et al.2026 · 0 citationsarXiv
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications2604.24668v3 · Zhenyu Zhao, Aparna Balagopalan, Adi Agrawal et al.2026 · 0 citationsarXiv
Backtracking Improves Generation Safety2409.14586v1 · Yiming Zhang, Jianfeng Chi, Hailey Nguyen et al.2024 · 1 citationarXiv
Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models2404.01295v1 · Yi-Lin Tuan, Xilun Chen, Eric Michael Smith et al.2024 · 0 citationsarXiv
Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems2311.06513v2 · Hsuan Su, Rebecca Qian, Chinnadhurai Sankar et al.2023 · 0 citationsarXiv
Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency2311.02772v2 · Sungho Jeon, Ching-Feng Yeh, Hakan Inan et al.2023 · 0 citationsarXiv
Entity Linking via Dual and Cross-Attention Encoders2004.03555v1 · Oshin Agarwal, Daniel M. Bikel2020 · 6 citationsarXiv
Career total: 36 works. 11 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.