Author name cluster

Ganqu Cui

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

ICLR Conference 2025 Conference Paper

Advancing LLM Reasoning Generalists with Preference Trees

Lifan Yuan
Ganqu Cui
Hanbin Wang
Ning Ding 0002
Xingyao Wang 0002
Boji Shan
Zeyuan Liu
Jia Deng

We introduce EURUS, a suite of large language models (LLMs) optimized for reasoning. Finetuned from Mistral-7B, Llama-3-8B, and Mixtral-8x22B, EURUS models achieve state-of-the-art results among open-source models on a diverse set of benchmarks covering mathematics, code generation, and logical reasoning problems. Notably, EURUX-8X22B outperforms GPT-3.5 Turbo in reasoning through a comprehensive benchmarking across 12 test sets covering five tasks. The strong performance of EURUS can be primarily attributed to ULTRAINTERACT, our newly-curated large-scale, high-quality training data dataset specifically designed for complex reasoning tasks. ULTRAINTERACT can be used in both supervised fine-tuning, preference learning, and reward modeling. It pairs each instruction with a preference tree consisting of (1) reasoning chains with diverse planning strategies in a unified format, (2) multi-turn interaction trajectories with the environment and the critique, and (3) pairwise positive and negative responses to facilitate preference learning. ULTRAINTERACT allows us to conduct an in-depth exploration of preference learning for reasoning tasks. Our investigation reveals that some well-established preference learning algorithms may be less suitable for reasoning tasks compared to their effectiveness in general conversations. The hypothesis is that in reasoning tasks, the space of correct answers is much smaller than that of incorrect ones, so it is necessary to explicitly increase the reward of chosen data. Therefore, in addition to increasing the reward margin as many preference learning algorithms do, the absolute values of positive responses’ rewards should be positive and may serve as a proxy for performance. Inspired by this, we derive a novel reward modeling objective and empirically that it leads to a stable reward modeling curve and better performance. Together with ULTRAINTERACT, we obtain a strong reward model.

Details

ICML Conference 2025 Conference Paper

Free Process Rewards without Process Labels

Lifan Yuan
Wendi Li
Huayu Chen
Ganqu Cui
Ning Ding 0002
Kaiyan Zhang
Bowen Zhou 0002
Zhiyuan Liu 0001

Different from its counterpart outcome reward models (ORMs), which evaluate the entire responses, a process reward model (PRM) scores a reasoning trajectory step by step, providing denser and more fine-grained rewards. However, training a PRM requires labels annotated at every intermediate step, presenting significant challenges for both manual and automatic data collection. This paper aims to address this challenge. Both theoretically and empirically, we show that an implicit PRM can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels. The only assumption is to parameterize the outcome reward as the log-likelihood ratios of the policy and reference models r$\phi$(y) = $\beta$ log $\pi$$\phi$(y) $\pi$ref(y), which can be optimized regardless of the specific choice of loss objectives. In experiments, we instantiate our implicit PRMs with various objectives and evaluate their performance on MATH. We show that our implicit PRM outperforms a strong MCTS-based baseline á la Math-Shepherd (Wang et al. , 2023) using less than 1/38 of the training data. Its performance can be further improved with majority voting. We further find that scaling up instructions and responses benefits our implicit PRM, and the latter brings a larger gain. Particularly, we find that our implicit PRM, when instantiated with the cross-entropy (CE) loss, is more data-efficient and can keep improving generation models even when trained with only one response per instruction, the setup that suffers from extreme data scarcity and imbalance. Further, instructions should be relevant to downstream tasks while the diversity of responses does not bring gains. Surprisingly, training on extra Math-Shepherd step labels brings no further improvements to our implicit PRM trained on only outcome data. We hope that our work will encourage a rethinking of PRM training approaches and contribute to making training PRMs more accessible.

Details

NeurIPS Conference 2025 Conference Paper

Learning to Reason under Off-Policy Guidance

Jianhao Yan
Yafu Li
Zican Hu
Zhi Wang
Ganqu Cui
Xiaoye Qu
Yu Cheng
Yue Zhang

Recent advances in large reasoning models (LRMs) demonstrate that sophisticated behaviors such as multi-step reasoning and self-reflection can emerge via reinforcement learning with verifiable rewards~(RLVR). However, existing RLVR approaches are inherently ``on-policy'', limiting learning to a model's own outputs and failing to acquire reasoning abilities beyond its initial capabilities. To address this issue, we introduce LUFFY (Learning to reason Under oFF-policY guidance), a framework that augments RLVR with off-policy reasoning traces. LUFFY dynamically balances imitation and exploration by combining off-policy demonstrations with on-policy rollouts during training. Specifically, LUFFY combines the Mixed-Policy GRPO framework, which has a theoretically guaranteed convergence rate, alongside policy shaping via regularized importance sampling to avoid superficial and rigid imitation during mixed-policy training. Compared with previous RLVR methods, LUFFY achieves an over +6. 4 average gain across six math benchmarks and an advantage of over +6. 2 points in out-of-distribution tasks. Most significantly, we show that LUFFY successfully trains weak models in scenarios where on-policy RLVR completely fails. These results provide compelling evidence that LUFFY transcends the fundamental limitations of on-policy RLVR and demonstrates the great potential of utilizing off-policy guidance in RLVR.

PDF Details

NeurIPS Conference 2025 Conference Paper

Scaling Physical Reasoning with the PHYSICS Dataset

Shenghe Zheng
Qianjia Cheng
Junchi Yao
Mengsong Wu
Haonan He
Ning Ding
Yu Cheng
Shuyue Hu

Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reasoning-intensive and essential to real-world understanding, received limited academic and industrial attention. This paper introduces PHYSICS, a dataset containing 16, 568 high-quality physics problems spanning subjects and difficulty levels, to facilitate this issue. Specifically, PHYSICS is curated with exercises from over 100 textbooks through a carefully designed pipeline for quality control. It covers five major physics domains: Mechanics, Electromagnetism, Thermodynamics, Optics, and Modern Physics. It also spans a wide range of difficulty levels, from high school to graduate-level physics courses. To utilize the data for improving and evaluating the model's physical reasoning capabilities, we split the dataset into training and test sets, and provide reasoning paths generated by powerful reasoning models for the training data to facilitate model training. In addition, for the evaluation part, we find that existing evaluation frameworks exhibit biases in aspects such as units, simplification, and precision in physics domain. To balance efficiency and accuracy, we introduce a Rule+Model evaluation framework tailored to physics problems. Our evaluations on current state-of-the-art open-source and proprietary models highlight the limitations of current models in handling physics-related tasks. We hope that our dataset and evaluation methodology will jointly advance the development of LLMs in the field of physics. The code and data can be found at: https: //github. com/Zhengsh123/PHYSICS.

PDF Details

NeurIPS Conference 2025 Conference Paper

TTRL: Test-Time Reinforcement Learning

Yuxin Zuo
Kaiyan Zhang
Li Sheng
Shang Qu
Ganqu Cui
Xuekai Zhu
Haozhan Li
Yuchen Zhang

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to ground-truth information. While this setting appears elusive, we find that common practices in Test-Time Scaling (TTS), such as majority voting, yield surprisingly effective rewards suitable for driving RL training. In this work, we introduce Test-Time Reinforcement Learning (TTRL), a novel method for training LLMs using RL on unlabeled data. TTRL enables self-evolution of LLMs by utilizing the priors in the pre-trained models. Our experiments demonstrate that TTRL consistently improves performance across a variety of tasks and models. Notably, TTRL boosts the pass@1 performance of Qwen-2. 5-Math-7B by approximately 211% on the AIME 2024 with only unlabeled test data. Furthermore, although TTRL is only supervised by the Maj@N metric, TTRL has demonstrated performance to consistently surpass the upper limit of the initial model, and approach the performance of models trained directly on test data with ground-truth labels. Our experimental findings validate the general effectiveness of TTRL across various tasks and highlight TTRL's potential for broader tasks and domains.

PDF Details

NeurIPS Conference 2024 Conference Paper

Noise Contrastive Alignment of Language Models with Explicit Rewards

Huayu Chen
Guande He
Lifan Yuan
Ganqu Cui
Hang Su
Jun Zhu

User intentions are typically formalized as evaluation rewards to be maximized when fine-tuning language models (LMs). Existing alignment methods, such as Direct Preference Optimization (DPO), are mainly tailored for pairwise preference data where rewards are implicitly defined rather than explicitly given. In this paper, we introduce a general framework for LM alignment, leveraging Noise Contrastive Estimation (NCE) to bridge the gap in handling reward datasets explicitly annotated with scalar evaluations. Our framework comprises two parallel algorithms, NCA and InfoNCA, both enabling the direct extraction of an LM policy from reward data as well as preference data. Notably, we show that the DPO loss is a special case of our proposed InfoNCA objective under pairwise preference settings, thereby integrating and extending current alignment theories. By comparing NCA and InfoNCA, we demonstrate that the well-observed decreasing-likelihood trend of DPO/InfoNCA is caused by their focus on adjusting relative likelihood across different responses. In contrast, NCA optimizes the absolute likelihood for each response, thereby effectively preventing the chosen likelihood from decreasing. We evaluate our methods in both reward and preference settings with Mistral-8$\times$7B and 7B models. Experiments suggest that InfoNCA/NCA surpasses various preference baselines when reward datasets are available. We also find NCA significantly outperforms DPO in complex reasoning tasks like math and coding.

PDF Details DOI

ICML Conference 2024 Conference Paper

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

Ganqu Cui
Lifan Yuan
Ning Ding 0002
Guanming Yao
Bingxiang He
Wei Zhu 0016
Yuan Ni
Guotong Xie

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in small sizes or limited topics of current datasets. This further hinders feedback learning as well as alignment research within the open-source community. To address this issue, we explore how to go beyond human feedback and collect high-quality AI feedback automatically for a scalable alternative. Specifically, we identify scale and diversity as the key factors for feedback data to take effect. Accordingly, we first broaden instructions and responses in both amount and breadth to encompass a wider range of user-assistant interactions. Then, we meticulously apply a series of techniques to mitigate annotation biases for more reliable AI feedback. We finally present UltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset, which contains over 1 million GPT-4 feedback for 250k user-assistant conversations from various aspects. Built upon UltraFeedback, we align a LLaMA-based model by best-of-$n$ sampling and reinforcement learning, demonstrating its exceptional performance on chat benchmarks. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models, serving as a solid foundation for future feedback learning research.

Details

NeurIPS Conference 2024 Conference Paper

UltraMedical: Building Specialized Generalists in Biomedicine

Kaiyan Zhang
Sihang Zeng
Ermo Hua
Ning Ding
Zhang-Ren Chen
Zhiyuan Ma
Haoxin Li
Ganqu Cui

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas. Recent advanced proprietary models such as GPT-4 and Gemini have achieved significant advancements in biomedicine, which have also raised privacy and security challenges. The construction of specialized generalists hinges largely on high-quality datasets, enhanced by techniques like supervised fine-tuning and reinforcement learning from human or AI feedback, and direct preference optimization. However, these leading technologies (e. g. , preference learning) are still significantly limited in the open source community due to the scarcity of specialized data. In this paper, we present the UltraMedical collections, which consist of high-quality manual and synthetic datasets in the biomedicine domain, featuring preference annotations across multiple advanced LLMs. By utilizing these datasets, we fine-tune a suite of specialized medical models based on Llama-3 series, demonstrating breathtaking capabilities across various medical benchmarks. Moreover, we develop powerful reward models skilled in biomedical and general reward benchmark, enhancing further online preference learning within the biomedical LLM community.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

Lifan Yuan
Yangyi Chen
Ganqu Cui
Hongcheng Gao
FangYuan Zou
Xingyi Cheng
Heng Ji
Zhiyuan Liu

This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We find that the distribution shift settings in previous studies commonly lack adequate challenges, hindering the accurate evaluation of OOD robustness. To address these issues, we propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts. Then we introduceBOSS, a Benchmark suite for Out-of-distribution robustneSS evaluation covering 5 tasks and 20 datasets. Based on BOSS, we conduct a series of experiments on pretrained language models for analysis and evaluation of OOD robustness. First, for vanilla fine-tuning, we examine the relationship between in-distribution (ID) and OOD performance. We identify three typical types that unveil the inner learningmechanism, which could potentially facilitate the forecasting of OOD robustness, correlating with the advancements on ID datasets. Then, we evaluate 5 classic methods on BOSS and find that, despite exhibiting some effectiveness in specific cases, they do not offer significant improvement compared to vanilla fine-tuning. Further, we evaluate 5 LLMs with various adaptation paradigms and find that when sufficient ID data is available, fine-tuning domain-specific models outperform LLMs on ID examples significantly. However, in the case of OOD instances, prioritizing LLMs with in-context learning yields better results. We identify that both fine-tuned small models and LLMs face challenges in effectively addressing downstream tasks. The code is public at https: //github. com/lifan-yuan/OOD_NLP.

PDF Details

NeurIPS Conference 2022 Conference Paper

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

Ganqu Cui
Lifan Yuan
Bingxiang He
Yangyi Chen
Zhiyuan Liu
Maosong Sun

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been proposed, it is of great significance to perform rigorous evaluations. However, we highlight two issues in previous backdoor learning evaluations: (1) The differences between real-world scenarios (e. g. releasing poisoned datasets or models) are neglected, and we argue that each scenario has its own constraints and concerns, thus requires specific evaluation protocols; (2) The evaluation metrics only consider whether the attacks could flip the models' predictions on poisoned samples and retain performances on benign samples, but ignore that poisoned samples should also be stealthy and semantic-preserving. To address these issues, we categorize existing works into three practical scenarios in which attackers release datasets, pre-trained models, and fine-tuned models respectively, then discuss their unique evaluation methodologies. On metrics, to completely evaluate poisoned samples, we use grammar error increase and perplexity difference for stealthiness, along with text similarity for validity. After formalizing the frameworks, we develop an open-source toolkit OpenBackdoor to foster the implementations and evaluations of textual backdoor learning. With this toolkit, we perform extensive experiments to benchmark attack and defense models under the suggested paradigm. To facilitate the underexplored defenses against poisoned datasets, we further propose CUBE, a simple yet strong clustering-based defense baseline. We hope that our frameworks and benchmarks could serve as the cornerstones for future model development and evaluations.

PDF Details

NeurIPS Conference 2022 Conference Paper

Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models

Biru Zhu
Yujia Qin
Ganqu Cui
Yangyi Chen
Weilin Zhao
Chong Fu
Yangdong Deng
Zhiyuan Liu

Despite the great success of pre-trained language models (PLMs) in a large set of natural language processing (NLP) tasks, there has been a growing concern about their security in real-world applications. Backdoor attack, which poisons a small number of training samples by inserting backdoor triggers, is a typical threat to security. Trained on the poisoned dataset, a victim model would perform normally on benign samples but predict the attacker-chosen label on samples containing pre-defined triggers. The vulnerability of PLMs under backdoor attacks has been proved with increasing evidence in the literature. In this paper, we present several simple yet effective training strategies that could effectively defend against such attacks. To the best of our knowledge, this is the first work to explore the possibility of backdoor-free adaptation for PLMs. Our motivation is based on the observation that, when trained on the poisoned dataset, the PLM's adaptation follows a strict order of two stages: (1) a moderate-fitting stage, where the model mainly learns the major features corresponding to the original task instead of subsidiary features of backdoor triggers, and (2) an overfitting stage, where both features are learned adequately. Therefore, if we could properly restrict the PLM's adaptation to the moderate-fitting stage, the model would neglect the backdoor triggers but still achieve satisfying performance on the original task. To this end, we design three methods to defend against backdoor attacks by reducing the model capacity, training epochs, and learning rate, respectively. Experimental results demonstrate the effectiveness of our methods in defending against several representative NLP backdoor attacks. We also perform visualization-based analysis to attain a deeper understanding of how the model learns different features, and explore the effect of the poisoning ratio. Finally, we explore whether our methods could defend against backdoor attacks for the pre-trained CV model. The codes are publicly available at https: //github. com/thunlp/Moderate-fitting.

PDF Details

IJCAI Conference 2019 Conference Paper

Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks

Cheng Yang
Jian Tang
Maosong Sun
Ganqu Cui
Zhiyuan Liu

Information diffusion prediction is an important task which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction which aims at guessing the next influenced user or macroscopic diffusion prediction which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, no previous works have suggested a unified model for both microscopic and macroscopic scales. In this paper, we propose a novel multi-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

PDF Details