10 papers · 1 filter
Not All Skills Help: Measuring and Repairing Agent Knowledge
Yixuan Wang, Yiyang Zhou, Yiming Liang +4
LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how…
DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
Xiang Feng, Jiawei Zhou, Zhangfeng Huang +6
Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer ac…
PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation
Ruidi Chang, Jiawei Zhou, Hanjie Chen
Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequen…
Distilling to Hybrid Attention Models via KL-Guided Layer Selection
Yanhong Li, Songlin Yang, Shawn Tan +4
Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising approach for improv…
OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking
Yanhong Li, Tianyang Xu, Kenan Tang +3
Knowledge-intensive question answering is central to large language models (LLMs) and is typically assessed using static benchmarks derived from sources like Wikipedia and textbook…
Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
Yanhong Li, Zixuan Lan, Jiawei Zhou
Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inpu…