6 papers · 1 filter
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
Jingyan Xu, Hong Shi, Yi Shan +4
Large language models answer knowledge-intensive questions using both parametric memory and retrieved evidence, but neither source is uniformly reliable. Retrieval can fill knowled…
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
Huashan Sun, Shengyi Liao, Yansen Han +8
Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primar…
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios
Bin Xu, Yu Bai, Huashan Sun +10
As large language models continue to advance, their application in educational contexts remains underexplored and under-optimized. In this paper, we address this gap by introducing…
Identifying and Analyzing Performance-Critical Tokens in Large Language Models
Yu Bai, Heyan Huang, Cesare Spinoso-Di Piano +4
In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task…
CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling
Yu Bai, Xiyuan Zou, Heyan Huang +4
Long sequence modeling has gained broad interest as large language models (LLMs) continue to advance. Recent research has identified that a large portion of hidden states within th…
How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
Heyan Huang, Yinghao Li, Huashan Sun +2
Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as…