Jiaheng Liu

DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning

Weize Liu, Yongchi Zhao, Yijia Luo +8

Large language models (LLMs) perform strongly on many language tasks but still struggle with complex multi-step reasoning across disciplines. Existing reasoning datasets often lack…

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Jiajun Shi, Jian Yang, Jiaheng Liu +26

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchm…

Think-J: Learning to Think for Generative LLM-as-a-Judge

Hui Huang, Yancheng He, Hongli Zhou +5

LLM-as-a-Judge refers to the automatic modeling of preferences for responses generated by Large Language Models (LLMs), which is of significant importance for both LLM evaluation a…

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models

Jianyu Liu, Hangyu Guo, Ranjie Duan +14

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks…

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

Yancheng He, Shilong Li, Jiaheng Liu +8

Recently, o1-like models have drawn significant attention, where these models produce the long Chain-of-Thought (CoT) reasoning steps to improve the reasoning abilities of existing…

AIR: Complex Instruction Generation via Automatic Iterative Refinement

Wei Liu, Yancheng He, Hui Huang +5

With the development of large language models, their ability to follow simple instructions has significantly improved. However, adhering to complex instructions remains a major cha…

"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models

Jihao Gu, Yingyao Wang, Pi Bu +17

The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge…

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training

Hui Huang, Jiaheng Liu, Yancheng He +5

Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignm…

ProgCo: Program Helps Self-Correction of Large Language Models

Xiaoshuai Song, Yanan Wu, Weixun Wang +3

Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectivel…

Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models

Yingshui Tan, Boren Zheng, Baihui Zheng +9

With the rapid advancement of Large Language Models (LLMs), significant safety concerns have emerged. Fundamentally, the safety of large language models is closely linked to the ac…

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models

Yancheng He, Shilong Li, Jiaheng Liu +15

New LLM evaluation benchmarks are important to align with the rapid development of Large Language Models (LLMs). In this work, we present Chinese SimpleQA, the first comprehensive…

2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision

Shilong Li, Yancheng He, Hui Huang +7

Recent advancements in Direct Preference Optimization (DPO) have significantly enhanced the alignment of Large Language Models (LLMs) with human preferences, owing to its simplicit…

MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models

Pei Wang, Yanan Wu, Zekun Wang +12

Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benc…

cs.CL2024★ 4 cited

DDK: Distilling Domain Knowledge for Efficient Large Language Models

Jiaheng Liu, Chenchen Zhang, Jinyang Guo +13

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distil…

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

Jie Liu, Zhanhui Zhou, Jiaheng Liu +4

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show th…

cs.CL2024★ 3 cited

D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models

Haoran Que, Jiaheng Liu, Ge Zhang +13

Continual Pre-Training (CPT) on Large Language Models (LLMs) has been widely used to expand the model's fundamental understanding of specific downstream domains (e.g., math and cod…

GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models

Shilong Li, Yancheng He, Hangyu Guo +9

Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts, c…

R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models

Ken Deng, Jiaheng Liu, He Zhu +13

Code completion models have made significant progress in recent years. Recently, repository-level code completion has drawn more attention in modern software development, and sever…

ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models

Yanan Wu, Jie Liu, Xingyuan Bu +10

This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unl…