Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows. Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges, MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging. Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification. Extensive evaluations of eight frontier LLMs reveal that while current models achieve meaningful iterative improvements, they still exhibit significant limitations in autonomously generating long-horizon solutions and efficiently resolving complex errors. Furthermore, MLE-Dojo’s flexible and extensible architecture seamlessly integrates diverse data sources, tools, and evaluation protocols, uniquely enabling model-based agent tuning and promoting interoperability, scalability, and reproducibility. We open-source our framework and benchmarks to foster community-driven innovation towards next-generation MLE agents.

Knowledge distillation is a popular technique to transfer knowledge from a large teacher model to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. Therefore, forcing the student to blindly imitate the unreliable teacher output distribution leads to inferior performance. To this end, we propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series. This perturbed loss implicitly transforms the original teacher into a proxy teacher with a distribution closer to the ground truth distribution. We establish the theoretical connection between this "distribution closeness'' and the student model generalizability, which enables us to select the PTLoss's perturbation coefficients in a principled way. Extensive experiments on six public benchmark datasets demonstrate the effectiveness of PTLoss with teachers of different scales.

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time alignment techniques, such as prompting and guided decoding, do not modify the underlying model, and their performance remains dependent on the original model's capabilities. To address these challenges, we propose aligning LLMs through representation editing. The core of our method is to view a pre-trained autoregressive LLM as a discrete-time stochastic dynamical system. To achieve alignment for specific objectives, we introduce external control signals into the state space of this language dynamical system. We train a value function directly on the hidden states according to the Bellman equation, enabling gradient-based optimization to obtain the optimal control signals at test time. Our experiments demonstrate that our method outperforms existing test-time alignment techniques while requiring significantly fewer resources compared to fine-tuning methods. Our code is available at [https://github.com/Lingkai-Kong/RE-Control](https://github.com/Lingkai-Kong/RE-Control).

We present PATRON, a prompt-based data selection method for pre-trained language model fine-tuning under cold-start scenarios, i.e., no initial labeled data are available. In PATRON, we design (1) a prompt-based uncertainty propagation approach to estimate the importance of data points and (2) a partition-then-rewrite (PTR) strategy to promote sample diversity when querying for annotations. Experiments on six text classification datasets show that PATRON outperforms the strongest cold-start data selection baselines by up to 6.9%. Besides, with 128 labels only, PATRON achieves 91.0% and 92.1% of the fully supervised performance based on vanilla fine-tuning and prompt-based learning respectively. Our implementation of PATRON will be published upon acceptance.

Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typically used in supervised learning where the data is labeled accurately. However, in weakly supervised learning, where most of the data is labeled through weak and noisy sources, it remains nontrivial to design effective boosting approaches. In this work, we show that the standard implementation of the convex combination of base learners can hardly work due to the presence of noisy labels. Instead, we propose LocalBoost, a novel framework for weakly-supervised boosting. LocalBoost iteratively boosts the ensemble model from two dimensions, i.e., intra-source and inter-source. The intra-source boosting introduces locality to the base learners and enables each base learner to focus on a particular feature regime by training new base learners on granularity-varying error regions. For the inter-source boosting, we leverage a conditional function to indicate the weak source where the sample is more likely to appear. To account for the weak labels, we further design an estimate-then-modify approach to compute the model weights. Experiments on seven datasets show that our method significantly outperforms vanilla boosting methods and other weakly-supervised methods.

Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult.We study interactive weakly-supervised learning-the problem of iteratively and automatically discovering novel labeling rules from data to improve the WSL model.Our proposed model, named PR-BOOST, achieves this goal via iterative promptbased rule discovery and model boosting.It uses boosting to identify large-error instances and then discovers candidate rules from them by prompting pre-trained LMs with rule templates.The candidate rules are judged by human experts, and the accepted rules are used to generate complementary weak labels and strengthen the current model.Experiments on four tasks show PRBOOST outperforms state-of-the-art WSL baselines up to 7.1%, and bridges the gaps with fully supervised models.Our Implementation is available at https: //github.com/rz-zhang/PRBoost.

On e-commerce platforms, predicting if two products are compatible with each other is an important functionality to achieve trustworthy product recommendation and search experience for consumers. However, accurately predicting product compatibility is difficult due to the heterogeneous product data and the lack of manually curated training data. We study the problem of discovering effective labeling rules that can enable weakly-supervised product compatibility prediction. We develop AMRule, a multi-view rule discovery framework that can (1) adaptively and iteratively discover novel rulers that can complement the current weakly-supervised model to improve compatibility prediction; (2) discover interpretable rules from both structured attribute tables and unstructured product descriptions. AMRule adaptively discovers labeling rules from large-error instances via a boosting-style strategy, the high-quality rules can remedy the current model's weak spots and refine the model iteratively. For rule discovery from structured product attributes, we generate composable high-order rules from decision trees; and for rule discovery from unstructured product descriptions, we generate prompt-based rules from a pre-trained language model. Experiments on 4 real-world datasets show that AMRule outperforms the baselines by $5.98%$ on average and improves rule quality and rule proposal efficiency.

Yue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, Chao Zhang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Active learning is an important technique for low-resource sequence labeling tasks.However, current active sequence labeling methods use the queried samples alone in each iteration, which is an inefficient way of leveraging human annotations.We propose a simple but effective data augmentation method to improve label efficiency of active sequence labeling.Our method, SeqMix, simply augments the queried samples by generating extra labeled sequences in each iteration.The key difficulty is to generate plausible sequences along with token-level labels.In SeqMix, we address this challenge by performing mixup for both sequences and token-level labels of the queried samples.Furthermore, we design a discriminator during sequence mixup, which judges whether the generated sequences are plausible or not.Our experiments on Named Entity Recognition and Event Detection tasks show that SeqMix can improve the standard active sequence labeling method by 2.27%-3.75% in terms of F 1 scores.The code and data for SeqMix can be found at https://github. com/rz-zhang/SeqMix.

Recent research has achieved impressive results in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains.

With the surge of deep learning, more and more attention has been put on the sequential recommender. It can be casted as sequence prediction problem, where we will predict the next item given the previous items. RNN approaches are able to capture the global sequential features from the data compared with the local features derived in Markov Chain methods. However, both approaches rely on the independence of users' sequences, which are not true in practice. We propose to formulate the sequential recommendation problem as collaborative sequence prediction problem to take the dependency of users' sequences into account. In order to solve the collaborative sequence prediction problem, we define the dynamic neighborhood relationship between users and introduce manifold regularization to RNN on the basis of the multi-facets of collaborative filtering, referred to as MrRNN. Experimental results on benchmark datasets show that our approach outperforms the state-of-the-art baselines.

BACKGROUND: MicroRNAs (miRNAs) are identified in nearly all plants where they play important roles in development and stress responses by target mRNA cleavage or translation repression. MiRNAs exert their functions by sequence complementation with target genes and hence their targets can be predicted using bioinformatics algorithms. In the past two decades, microarray technology has been employed to study genes involved in important biological processes such as biotic response, abiotic response, and specific tissues and developmental stages, many of which are miRNA targets. Despite their value in assisting research work for plant biologists, miRNA target genes are difficult to access without pre-processing and assistance of necessary analytical and visualization tools because they are embedded in a large body of microarray data that are scattered around in public databases. DESCRIPTION: Plant MiRNA Target Expression Database (PMTED) is designed to retrieve and analyze expression profiles of miRNA targets represented in the plethora of existing microarray data that are manually curated. It provides a Basic Information query function for miRNAs and their target sequences, gene ontology, and differential expression profiles. It also provides searching and browsing functions for a global Meta-network among species, bioprocesses, conditions, and miRNAs, meta-terms curated from well annotated microarray experiments. Networks are displayed through a Cytoscape Web-based graphical interface. In addition to conserved miRNAs, PMTED provides a target prediction portal for user-defined novel miRNAs and corresponding target expression profile retrieval. Hypotheses that are suggested by miRNA-target networks should provide starting points for further experimental validation. CONCLUSIONS: PMTED exploits value-added microarray data to study the contextual significance of miRNA target genes and should assist functional investigation for both miRNAs and their targets. PMTED will be updated over time and is freely available for non-commercial use at http://pmted.agrinome.org.