1 citations · 1 across the 2 of their papers we have counts for
4 papers
HiNS: Hierarchical Negative Sampling for More Comprehensive Memory Retrieval Embedding Model
Motong Tian, Allen P. Wong, Mingjun Mao +1
Memory-augmented language agents rely on embedding models for effective memory retrieval. However, existing training data construction overlooks a critical limitation: the hierarch…
Evaluating Large Language Models on Controlled Generation Tasks
Jiao Sun, Yufei Tian, Wangchunshu Zhou +6
While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc,…
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
Yifan Hou, Jiaoda Li, Yu Fei +5
Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheatin…
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
Ruida Wang, Wangchunshu Zhou, Mrinmaya Sachan
*Data Synthesis* is a promising way to train a small model with very little labeled data. One approach for data synthesis is to leverage the rich knowledge from large language mode…