63 citations · 79 across the 19 of their papers we have counts for
20 papers
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Zhuowen Han, Jinwei Xiao, Zhengxi Lu +9
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO)…
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models
Ling Shi, Xinwei Wu, Xiaohu Zhao +7
While mechanistic interpretability tools like Sparse Autoencoders (SAEs) can uncover meaningful features within Large Language Models (LLMs), a critical gap remains in transforming…
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
Dan Shi, Zhuowen Han, Simon Ostermann +3
Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (S…
Thinking Seeds: Restarting On-Policy RL from the Model's Own Past Reasoning States
Lei Yang, Wei Bi, Chenxi Sun +2
On-policy reinforcement learning (RL) for language models trains on the reasoning states visited by the current policy. As training sharpens the policy, some states reached by earl…
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
Renren Jin, Pengzhi Gao, Yuqi Ren +6
Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the ent…
TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation
Renren Jin, Tianhao Shen, Xinwei Wu +9
Conducting supervised and preference fine-tuning of large language models (LLMs) requires high-quality datasets to improve their ability to follow instructions and align with human…
ProBench: Benchmarking Large Language Models in Competitive Programming
Lei Yang, Renren Jin, Ling Shi +3
With reasoning language models such as OpenAI-o3 and DeepSeek-R1 emerging, large language models (LLMs) have entered a new phase of development. However, existing benchmarks for co…
Large Language Model Safety: A Holistic Survey
Dan Shi, Tianhao Shen, Yufei Huang +10
The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural lang…
Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
Hang Zhou, Yehui Tang, Haochen Qin +5
The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, colle…
CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models
Ling Shi, Deyi Xiong
Large language models (LLMs) are possessed of numerous beneficial capabilities, yet their potential inclination harbors unpredictable risks that may materialize in the future. We h…
LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models
Chuang Liu, Renren Jin, Yuqi Ren +1
Chinese Large Language Models (LLMs) have recently demonstrated impressive capabilities across various NLP benchmarks and real-world applications. However, the existing benchmarks…
OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety
Chuang Liu, Linhao Yu, Jiaxuan Li +11
The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluat…
FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models
Yan Liu, Renren Jin, Ling Shi +2
To thoroughly assess the mathematical reasoning abilities of Large Language Models (LLMs), we need to carefully curate evaluation datasets covering diverse mathematical concepts an…
A Comprehensive Evaluation of Quantization Strategies for Large Language Models
Renren Jin, Jiangcun Du, Wuwei Huang +4
Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficul…
CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models
Dan Shi, Chaobin You, Jiantao Huang +2
As an indispensable ingredient of intelligence, commonsense reasoning is crucial for large language models (LLMs) in real-world scenarios. In this paper, we propose CORECODE, a dat…
RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models
Tianhao Shen, Sun Li, Quan Tu +1
The rapid evolution of large language models necessitates effective benchmarks for evaluating their role knowledge, which is essential for establishing connections with the real wo…
Evaluating Large Language Models: A Comprehensive Survey
Zishan Guo, Renren Jin, Chuang Liu +8
Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous dow…
FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models
Yimin Jing, Renren Jin, Jiahao Hu +4
The effective assessment of the instruction-following ability of large language models (LLMs) is of paramount importance. A model that cannot adhere to human instructions might be…
Towards a Deep Understanding of Multilingual End-to-End Speech Translation
Haoran Sun, Xiaohu Zhao, Yikun Lei +2
In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over…
Is Robustness Transferable across Languages in Multilingual Neural Machine Translation?
Leiyu Pan, Supryadi, Deyi Xiong
Robustness, the ability of models to maintain performance in the face of perturbations, is critical for developing reliable NLP systems. Recent studies have shown promising results…