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…
On the Predictive Power of Representation Dispersion in Language Models
Yanhong Li, Ming Li, Karen Livescu +1
We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely ten…
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…