10 papers
PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows
Hongliang Li, Yijin Liu, Zhiwei Zhang +5
While Large Language Model (LLM) agents excel at monolingual long-horizon planning and tool use, enterprise workflows inherently require processing multilingual resources across ex…
SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
Yijie Chen, Yijin Liu, Fandong Meng
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has emerged as the standard post-training paradigm for large language models (LLMs). However, the conventional…
Warmup-Distill: Bridge the Distribution Mismatch between Teacher and Student before Knowledge Distillation
Zengkui Sun, Yijin Liu, Fandong Meng +3
The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller o…
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping
Yijie Chen, Yijin Liu, Fandong Meng +3
Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identi…
Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words
Yijie Chen, Yijin Liu, Fandong Meng +3
Gender bias has been a focal point in the study of bias in machine translation and language models. Existing machine translation gender bias evaluations are primarily focused on ma…
Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
Zengkui Sun, Yijin Liu, Jiaan Wang +4
Recently, Knowledge Editing has received increasing attention, since it could update the specific knowledge from outdated ones in pretrained models without re-training. However, as…