2.7k citations · 2.7k across the 19 of their papers we have counts for
7 papers · 1 filter
Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization
Xinsong Feng, Peng Du, Zhizhuo Yang +3
Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive (AR) decoding. However, most…
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Peng Du, Kiran Kamble, Rakshith Vasudev +5
Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Su…
Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
Shelly Bensal, Axel Magnuson, Aparna Balagopalan +1
Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time. We show they also make models less correct by amplifying sycophancy, wherein models p…
Auditing LLM Benchmarks with Item Response Theory
Sander Land, Daniel M. Bikel
LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-based indicator that surfaces li…
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens
Zhenyu Zhao, Sander Land, Daniel M. Bikel +1
Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that r…
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
Zhenyu Zhao, Aparna Balagopalan, Adi Agrawal +3
Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems. One failure mode that LLMs frequently displa…