📝 Biography

🔥 Recent News

• Nov, 2025. SparK accepted to AAAI 2026!


• Oct, 2025. Awarded National Scholarship by Ministry of Education at CASIA!


• May, 2025. ETAPP accepted to ACL 2025!


• Dec, 2024. NesyCD and CITI accepted to AAAI 2025!


• Nov, 2024. AAG and SKIntern accepted to COLING 2025!


• Sep, 2024. TAGI accepted to NeurIPS 2024!


• Jun, 2023. Graduated from NCEPU with honor: awarded Outstanding Graduate by Beijing Ministry of Education and by NCEPU!


• Dec, 2022. Awarded National Scholarship by Ministry of Education at NCEPU!


• Dec, 2021. Awarded National Scholarship by Ministry of Education at NCEPU!

📒 Publications

Check my Google Scholar for more information!

(* stands for equal contribution. Listed in reverse chronological order.)

• SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning   
  Huanxuan Liao, Yixing Xu, Shizhu He, Guanchen Li, Xuanwu Yin, Dong Li, Emad Barsoum, Jun Zhao, Kang Liu   
  In AAAI 2026.
  
   

   

   

   

   

   

   
  @article{liao2025spark, title={SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning}, author={Liao, Huanxuan and Xu, Yixing and He, Shizhu and Li, Guanchen and Yin, Xuanwu and Li, Dong and Barsoum, Emad and Zhao, Jun and Liu, Kang}, journal={arXiv preprint arXiv:2508.15212}, year={2025} } Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address this issue by compressing the KV cache along the \textit{temporal} axis through strategies such as token eviction or merging to reduce memory and computational overhead. However, these methods often neglect fine-grained importance variations across feature dimensions (i.e., the \textit{channel axis}), thereby limiting their ability to effectively balance efficiency and model accuracy.In reality, we observe that channel saliency varies dramatically across both queries and positions: certain feature channels carry near-zero information for a given query, while others spike in relevance. To address this oversight, we propose \our, a training-free plug-and-play method that applies unstructured sparsity by pruning KV at the channel level, while dynamically restoring the pruned entries during attention score computation. Notably, our approach is orthogonal to existing KV compression and quantization techniques, making it compatible for integration with them to achieve further acceleration. By reducing channel-level redundancy, \our{} enables processing of longer sequences within the same memory budget. For sequences of equal length, \our{} not only preserves or improves model accuracy but also reduces KV cache storage by over $30\%$ compared to eviction-based methods. Furthermore, even in an aggressive pruning ratio of $80\%$, \our{} maintains performance with less degradation than $5\%$ compared to the based eviction method, demonstrating its robustness and effectiveness.


• Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
  Huanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Kang Liu, Jun Zhao   
  In AAAI 2025.
  
   

   

   

   

   

   

   
  @inproceedings{liao2025neural, title={Neural-symbolic collaborative distillation: Advancing small language models for complex reasoning tasks}, author={Liao, Huanxuan and He, Shizhu and Xu, Yao and Zhang, Yuanzhe and Liu, Kang and Zhao, Jun}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={39}, number={23}, pages={24567--24575}, year={2025} } In this paper, we propose Neural-Symbolic Collaborative Distillation (NesyCD), a novel knowledge distillation method for learning the complex reasoning abilities of Large Language Models (LLMs, e.g., \textgreater 13B). We argue that complex reasoning tasks are difficult for Small Language Models (SLMs, e.g., ≤ 7B), as these tasks demand not only general cognitive abilities but also specialized knowledge, which is often sparse and difficult for these neural-based SLMs to effectively capture. Therefore, NesyCD distills the general capabilities and specialized knowledge in LLMs using different manners. On the one hand, we distill only general abilities from teacher LLMs into the student SLMs of parameterized neural networks. On the other hand, for the specialized abilities and uncommon knowledge of a complex reasoning task, we employ a symbolic knowledge distillation approach to obtain and store the specialized knowledge within a symbolic knowledge base (KB). By decoupling general and specialized capabilities, the proposed NesyCD can achieve superior performance cost-effectively, utilizing smaller models and blending parameterized neural networks with symbolic KB. Moreover, the specialized KB generalizes well and is comprehended and manipulated by humans. Our experiments show that NesyCD significantly boosts SLMs' complex reasoning performance on in-domain (BBH, GSM8K) and out-of-domain (AGIEval, ARC) datasets. Notably, our approach enabled the LLaMA3-8B and Qwen2-7B to surpass GPT-3.5-turbo in performance and come close to matching LLaMA3-70B, despite the latter having nine times more parameters.


• SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models   
  Huanxuan Liao, Shizhu He, Yupu Hao, Xiang Li, Yuanzhe Zhang, Jun Zhao, Kang Liu   
  In COLING 2025.
  
   

   

   

   

   

   

   
  @inproceedings{liao2025skintern, title={SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models}, author={Liao, Huanxuan and He, Shizhu and Hao, Yupu and Li, Xiang and Zhang, Yuanzhe and Zhao, Jun and Liu, Kang}, booktitle={Proceedings of the 31st International Conference on Computational Linguistics}, pages={3203--3221}, year={2025} } Small Language Models (SLMs) are attracting attention due to the high computational demands and privacy concerns of Large Language Models (LLMs). Some studies fine-tune SLMs using Chains of Thought (CoT) data distilled from LLMs, aiming to enhance their reasoning ability. Furthermore, Some CoT distillation methods introduce external symbolic knowledge into the generation process to improve the limited knowledge memory, reasoning ability and out-of-domain (OOD) generalization of SLMs. However, the introduction of symbolic knowledge increases computational overhead and introduces potential noise. In this paper, we introduce SKIntern, an innovative approach that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process, guided by a predefined linear decay schedule under curriculum learning. By efficiently internalizing knowledge, SKIntern reduces computational overhead and speeds up the reasoning process by focusing solely on the question during inference. It outperforms state-of-the-art baselines by over 5\%, while reducing inference costs (measured in FLOPs) by up to 4× across a wide range of SLMs in both in-domain (ID) and out-of-domain (OOD) tasks.


• AAG: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering   
  Huanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Kang Liu, Shengping Liu, Jun Zhao   
  In COLING 2025.
  
   

   

   

   

   

   

   

   

  
  @inproceedings{liao2025awakening, title={Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering}, author={Liao, Huanxuan and He, Shizhu and Xu, Yao and Zhang, Yuanzhe and Liu, Shengping and Liu, Kang and Zhao, Jun}, booktitle={Proceedings of the 31st International Conference on Computational Linguistics}, pages={1333--1352}, year={2025} } Retrieval-Augmented-Generation and Gener-ation-Augmented-Generation have been proposed to enhance the knowledge required for question answering over Large Language Models (LLMs). However, the former relies on external resources, and both require incorporating explicit documents into the context, which increases execution costs and susceptibility to noise data. Recent works indicate that LLMs have modeled rich knowledge, albeit not effectively triggered or awakened. Inspired by this, we propose a novel knowledge-augmented framework, Imagination-Augmented-Generation (IAG), which simulates the human capacity to compensate for knowledge deficits while answering questions solely through imagination, thereby awakening relevant knowledge in LLMs without relying on external resources. Guided by IAG, we propose an imagine richer context method for question answering (IMcQA). IMcQA consists of two modules: explicit imagination, which generates a short dummy document by learning from long context compression, and implicit imagination, which creates flexible adapters by distilling from a teacher model with a long context. Experimental results on three datasets demonstrate that IMcQA exhibits significant advantages in both open-domain and closed-book settings, as well as in out-of-distribution generalization.


• From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
  Huanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Yanchao Hao, Shengping Liu, Kang Liu, Jun Zhao   
  In NeurIPS 2024.
  
   

   

   

   

   

   

   

   

  
  @article{liao2024instance, title={From instance training to instruction learning: Task adapters generation from instructions}, author={Liao, Huanxuan and He, Shizhu and Xu, Yao and Zhang, Yuanzhe and Hao, Yanchao and Liu, Shengping and Liu, Kang and Zhao, Jun}, journal={Advances in Neural Information Processing Systems}, volume={37}, pages={45552--45577}, year={2024} } Large language models (LLMs) have acquired the ability to solve general tasks by utilizing instruction finetuning (IFT). However, IFT still relies heavily on instance training of extensive task data, which greatly limits the adaptability of LLMs to real-world scenarios where labeled task instances are scarce and broader task generalization becomes paramount. Contrary to LLMs, humans acquire skills and complete tasks not merely through repeated practice but also by understanding and following instructional guidelines. This paper is dedicated to simulating human learning to address the shortcomings of instance training, focusing on instruction learning to enhance cross-task generalization. Within this context, we introduce Task Adapters Generation from Instructions (TAGI), which automatically constructs the task-specific model in a parameter generation manner based on the given task instructions without retraining for unseen tasks. Specifically, we utilize knowledge distillation to enhance the consistency between TAGI developed through Learning with Instruction and task-specific models developed through Training with Instance, by aligning the labels, output logits, and adapter parameters between them. TAGI is endowed with cross-task generalization capabilities through a two-stage training process that includes hypernetwork pretraining and finetuning. We evaluate TAGI on the Super-Natural Instructions and P3 datasets. The experimental results demonstrate that TAGI can match or even outperform traditional meta-trained models and other hypernetwork models, while significantly reducing computational requirements.


• Dynamic Weighted Neural Bellman-Ford Network for Knowledge Graph Reasoning   
  Huanxuan Liao, Shizhu He, Yao Xu, Kang Liu, Jun Zhao   
  Accepted to CCKS 2023.
  
   

   

   
  @inproceedings{liao2023dynamic, title={Dynamic Weighted Neural Bellman-Ford Network for Knowledge Graph Reasoning}, author={Liao, Huanxuan and He, Shizhu and Xu, Yao and Liu, Kang and Zhao, Jun}, booktitle={China Conference on Knowledge Graph and Semantic Computing}, pages={3--16}, year={2023}, organization={Springer} } Recent studies have shown that subgraphs of the head entity, such as related relations and neighborhoods, are helpful for Knowledge Graph Reasoning (KGR). However, prior studies tend to focus solely on enhancing entity representations using related relations, with little attention paid to the impact of different relations on different entities and their importance in various reasoning paths. Meanwhile, conventional Graph Neural Networks (GNNs) utilized for KGR consider simultaneously neighboring nodes and connected relations of the head entity but typically use a standard message-passing paradigm over the entire Knowledge Graph (KG). This results in over-smoothed representations and limits efficiency. To address the above-mentioned limitations of existing methods, we propose a Dynamic Weighted Neural Bellman-Ford Network (DyNBF) for KGR, which utilizes relation weights generated from subgraphs to compute only the most relevant relations and entities. This way, we can integrate multiple reasoning paths more flexibly to achieve better interpretable reasoning, while scaling more easily to more complex and larger KGs. DyNBF consists of two key modules: 1) a transformer-based relation weights generator module, which computes the weights of different relations on the path with a sequence-to-sequence model, and 2) an NBFNet-based logic reasoner module, which obtains entity representations and conducts fact prediction with dynamic weights from the previous module. Empirical results on three standard KGR datasets demonstrate that the proposed approach can generate explainable reasoning paths and obtain competitive performance.

• Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention   
  Huanxuan Liao, Wen Hu, Yao Xu, Shizhu He, Jun Zhao, Kang Liu   
  Preprint, 2025.
  
   

   

   

   

   

   

   
  @article{liao2025beyond, title={Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention}, author={Liao, Huanxuan and Hu, Wen and Xu, Yao and He, Shizhu and Zhao, Jun and Liu, Kang}, journal={arXiv preprint arXiv:2505.15774}, year={2025} } Large Language Models (LLMs) encounter significant challenges in long-sequence inference due to computational inefficiency and redundant processing, driving interest in context compression techniques. Existing methods often rely on token importance to perform hard local compression or encode context into latent representations for soft global compression. However, the uneven distribution of textual content relevance and the diversity of demands for user instructions mean these approaches frequently lead to the loss of potentially valuable information. To address this, we propose Hybrid Context Compression (HyCo2) for LLMs, which integrates both global and local perspectives to guide context compression while retaining both the essential semantics and critical details for task completion. Specifically, we employ a hybrid adapter to refine global semantics with the global view, based on the observation that different adapters excel at different tasks. Then we incorporate a classification layer that assigns a retention probability to each context token based on the local view, determining whether it should be retained or discarded. To foster a balanced integration of global and local compression, we introduce auxiliary paraphrasing and completion pretraining before instruction tuning. This promotes a synergistic integration that emphasizes instruction-relevant information while preserving essential local details, ultimately balancing local and global information retention in context compression. Experiments show that our HyCo2 method significantly enhances long-text reasoning while reducing token usage. It improves the performance of various LLM series by an average of 13.1\% across seven knowledge-intensive QA benchmarks. Moreover, HyCo2 matches the performance of uncompressed methods while reducing token consumption by 88.8\%


• DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning   
  Huanxuan Liao, Shizhu He, Yupu Hao, Jun Zhao, Kang Liu   
  Preprint, 2025.
  
   

   

   

   

   

   

   
  @article{liao2025data, title={DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning}, author={Liao, Huanxuan and He, Shizhu and Hao, Yupu and Zhao, Jun and Liu, Kang}, journal={arXiv preprint arXiv:2502.11482}, year={2025} } Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent rehearsal-free methods employ model-based and regularization-based strategies to address this issue. However, these approaches often neglect the model's plasticity, which is crucial to achieving optimal performance on newly learned tasks. Consequently, a key challenge in CL is striking a balance between preserving plasticity and mitigating CF. To tackle this challenge, we propose the Decomposed Attention-based Task Adaptation (DATA), which explicitly decouples and learns both task-specific and task-shared knowledge using high-rank and low-rank task adapters (e.g., LoRAs). For new tasks, DATA dynamically adjusts the weights of adapters of different ranks based on their relevance and distinction from previous tasks, allowing the model to acquire new task-specific skills while effectively retaining previously learned knowledge. Specifically, we implement a decomposed component weighting strategy comprising learnable components that collectively generate attention-based weights, allowing the model to integrate and utilize diverse knowledge from each DATA. Extensive experiments on three widely used benchmarks demonstrate that our proposed method achieves state-of-the-art performance. Notably, our approach significantly enhances model plasticity and mitigates CF by extending learnable components and employing stochastic restoration during training iterations.


• A Comprehensive Survey on Long Context Language Modeling   
  LCLM-Horizon: Jiaheng Liu, Dawei Zhu, Zhiqi Bai, Yancheng He, Huanxuan Liao, Haoran Que, Zekun Wang, Chenchen Zhang, Ge Zhang, Jiebin Zhang, Yuanxing Zhang, Zhuo Chen, Hangyu Guo, Shilong Li, Ziqiang Liu, Yong Shan, Yifan Song, Jiayi Tian, Wenhao Wu, Zhejian Zhou, Ruijie Zhu, Junlan Feng, Yang Gao, Shizhu He, Zhoujun Li, Tianyu Liu, Fanyu Meng, Wenbo Su, Yingshui Tan, Zili Wang, Jian Yang, Wei Ye, Bo Zheng, Wangchunshu Zhou, Wenhao Huang, Sujian Li, Zhaoxiang Zhang   
  Preprint, 2025.   
  Core Contributor
  
   

   

   

   

   

   

   
  @article{liu2025comprehensive, title={A Comprehensive Survey on Long Context Language Modeling}, author={Liu, Jiaheng and Zhu, Dawei and Bai, Zhiqi and He, Yancheng and Liao, Huanxuan and Que, Haoran and Wang, Zekun and Zhang, Chenchen and Zhang, Ge and Zhang, Jiebin and others}, journal={arXiv preprint arXiv:2503.17407}, year={2025} } Efficient processing of long contexts has been a persistent pursuit in Natural Language Processing. With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models (LCLMs) that can process and analyze extensive inputs in an effective and efficient way. In this paper, we present a comprehensive survey on recent advances in long-context modeling for large language models. Our survey is structured around three key aspects: how to obtain effective and efficient LCLMs, how to train and deploy LCLMs efficiently, and how to evaluate and analyze LCLMs comprehensively. For the first aspect, we discuss data strategies, architectural designs, and workflow approaches oriented with long context processing. For the second aspect, we provide a detailed examination of the infrastructure required for LCLM training and inference. For the third aspect, we present evaluation paradigms for long-context comprehension and long-form generation, as well as behavioral analysis and mechanism interpretability of LCLMs. Beyond these three key aspects, we thoroughly explore the diverse application scenarios where existing LCLMs have been deployed and outline promising future development directions. This survey provides an up-to-date review of the literature on long-context LLMs, which we wish to serve as a valuable resource for both researchers and engineers.


• Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity   
  Yupu Hao, Pengfei Cao, Zhuoran Jin, Huanxuan Liao, Yubo Chen, Kang Liu, Jun Zhao   
  In ACL 2025.
  
   

   

   

   

   

   

   
  @article{hao2025evaluating, title={Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity}, author={Hao, Yupu and Cao, Pengfei and Jin, Zhuoran and Liao, Huanxuan and Chen, Yubo and Liu, Kang and Zhao, Jun}, journal={arXiv preprint arXiv:2503.00771}, year={2025} } Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. However, most of the current benchmarks primarily focus on either personalization of text generation or direct tool-utilizing, without considering both. In this work, we introduce a novel benchmark ETAPP for evaluating personalized tool invocation, establishing a sandbox environment, and a comprehensive dataset of 800 testing cases covering diverse user profiles. To improve the accuracy of our evaluation, we propose a key-point-based LLM evaluation method, mitigating biases in the LLM-as-a-judge system by manually annotating key points for each test case and providing them to LLM as the reference. Additionally, we evaluate the excellent LLMs and provide an in-depth analysis. Furthermore, we investigate the impact of different tool-invoking strategies on LLMs' personalization performance and the effects of fine-tuning in our task. The effectiveness of our preference-setting and key-point-based evaluation method is also validated. Our findings offer insights into improving personalized LLM agents.


• CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance   
  Yupu Hao, Pengfei Cao, Zhuoran Jin, Huanxuan Liao, Yubo Chen, Kang Liu, Jun Zhao   
  In AAAI 2025.
  
   

   

   

   

   

   

   
  @inproceedings{hao2025citi, title={CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance}, author={Hao, Yupu and Cao, Pengfei and Jin, Zhuoran and Liao, Huanxuan and Chen, Yubo and Liu, Kang and Zhao, Jun}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={39}, number={22}, pages={23996--24004}, year={2025} } Tool learning enables the Large Language Models (LLMs) to interact with the external environment by invoking tools, enriching the accuracy and capability scope of LLMs. However, previous works predominantly focus on improving model's tool-utilizing accuracy and the ability to generalize to new, unseen tools, excessively forcing LLMs to adjust specific tool-invoking pattern without considering the harm to model's general performance. This deviates from the actual applications and original intention of integrating tools to enhance model. To tackle this problem, we dissect the capability trade-offs by examining the hidden representation changes and the gradient-based importance score of model's components. Based on the analysis result, we propose a Component Importance-based Tool-utilizing ability Injection method (CITI). According to the gradient-based importance score of different components, it alleviates the capability conflicts caused by fine-tuning process by applying distinct training strategies to different components. CITI applies Mixture-Of-LoRA (MOLoRA) for important components. Meanwhile, it fine-tunes the parameters of few components deemed less important in the backbone of the LLM, while keeping other parameters frozen. CITI can effectively enhance the model's tool-utilizing capability without excessively compromising its general performance. Experimental results demonstrate that our approach achieves outstanding performance across a range of evaluation metrics.


• Better wit than wealth: Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement   
  Yuqiao Tan, Shizhu He, Huanxuan Liao, Jun Zhao, Kang Liu   
  Preprint, 2025.
  
   

   

   

   

   

   

   

   

  
  @article{tan2025better, title={Better wit than wealth: Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement}, author={Tan, Yuqiao and He, Shizhu and Liao, Huanxuan and Zhao, Jun and Liu, Kang}, journal={arXiv preprint arXiv:2503.23895}, year={2025} } Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it improves reliability by providing factual texts, it significantly increases inference costs as context length grows and introduces challenging issue of RAG hallucination, primarily caused by the lack of corresponding parametric knowledge in LLMs. An efficient solution is to enhance the knowledge of LLMs at test-time. Parametric RAG (PRAG) addresses this by embedding document into LLMs parameters to perform test-time knowledge enhancement, effectively reducing inference costs through offline training. However, its high training and storage costs, along with limited generalization ability, significantly restrict its practical adoption. To address these challenges, we propose Dynamic Parametric RAG (DyPRAG), a novel framework that leverages a lightweight parameter translator model to efficiently convert documents into parametric knowledge. DyPRAG not only reduces inference, training, and storage costs but also dynamically generates parametric knowledge, seamlessly enhancing the knowledge of LLMs and resolving knowledge conflicts in a plug-and-play manner at test-time. Extensive experiments on multiple datasets demonstrate the effectiveness and generalization capabilities of DyPRAG, offering a powerful and practical RAG paradigm which enables superior knowledge fusion and mitigates RAG hallucination in real-world applications.


• VaiBot: Shuttle Between the Instructions and Parameters of Large Language Models   
  Wangtao Sun, Haotian Xu, Huanxuan Liao, Xuanqing Yu, Zhongtao Jiang, Shizhu He, Jun Zhao, Kang Liu   
  Preprint, 2025.
  
   

   

   

   

   

   

   
  @article{sun2025vaibot, title={VaiBot: Shuttle Between the Instructions and Parameters}, author={Sun, Wangtao and Xu, Haotian and Liao, Huanxuan and Yu, Xuanqing and Jiang, Zhongtao and He, Shizhu and Zhao, Jun and Liu, Kang}, journal={arXiv preprint arXiv:2502.02315}, year={2025} } How to interact with LLMs through \emph{instructions} has been widely studied by researchers. However, previous studies have treated the emergence of instructions and the training of LLMs on task data as separate processes, overlooking the inherent unity between the two. This paper proposes a neural network framework, VaiBot, that integrates VAE and VIB, designed to uniformly model, learn, and infer both deduction and induction tasks under LLMs. Through experiments, we demonstrate that VaiBot performs on par with existing baseline methods in terms of deductive capabilities while significantly surpassing them in inductive capabilities. We also find that VaiBot can scale up using general instruction-following data and exhibits excellent one-shot induction abilities. We finally synergistically integrate the deductive and inductive processes of VaiBot. Through T-SNE dimensionality reduction, we observe that its inductive-deductive process significantly improves the distribution of training parameters, enabling it to outperform baseline methods in inductive reasoning tasks.


• LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models   
  Yixuan Weng, Zhiqi Wang, Huanxuan Liao, Shizhu He, Shengping Liu, Kang Liu, Jun Zhao   
  Preprint, 2023.
  
   

   

   

   

   

   

   

   

  
  @article{weng2023lmtuner, title={LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models}, author={Weng, Yixuan and Wang, Zhiqi and Liao, Huanxuan and He, Shizhu and Liu, Shengping and Liu, Kang and Zhao, Jun}, journal={arXiv preprint arXiv:2308.10252}, year={2023} } With the burgeoning development in the realm of large language models (LLMs), the demand for efficient incremental training tailored to specific industries and domains continues to increase. Currently, the predominantly employed frameworks lack modular design, it often takes a lot of coding work to kickstart the training of LLM. To address this, we present "LMTuner", a highly usable, integrable, and scalable system for training LLMs expeditiously and with minimal user-input. LMTuner comprises three main modules - the Interaction, Training, and Inference Modules. We advocate that LMTuner's usability and integrality alleviate the complexities in training large language models. Remarkably, even a novice user could commence training large language models within five minutes. Furthermore, it integrates DeepSpeed frameworks and supports Efficient Fine-Tuning methodologies like Low Rank Adaptation (LoRA), Quantized LoRA (QLoRA), etc., enabling the training of language models scaling from 300M to a whopping 130B parameters using a single server. The LMTuner's homepage (this https URL screencast video (this https URL) are now publicly available.

💻 Services

• Conference Reviewing : ACL ARR 2024, 2025. NeurIPS 2025. ICLR 2025. AAAI 2026.
• Comunity : Awesome-LLM-Long-Context-Modeling Github 1.8k+ Stars.