Author name cluster

Fei Mi

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.

10 papers

2 author rows

AAAI Conference 2026 Conference Paper

EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing

Fan Gao
Dongyuan Li
Ding Xia
Fei Mi
Yasheng Wang
Lifeng Shang
Baojun Wang

Prompt-based essay writing is an effective and common way to assess students' critical thinking skills. Recent work has evaluated the impressive capabilities of Large Language Models (LLMs) on this task. However, most studies focus primarily on English. Those examining LLMs' performance in Chinese often rely on coarse-grained text quality metrics, overlooking the structural and rhetorical complexities of Chinese essays, particularly across diverse genres. We therefore propose EssayBench, a multi-genre benchmark specifically designed for Chinese essay writing, along with a fine-grained, genre-specific scoring framework that hierarchically aggregates scores to better align with human preferences. The dataset comprises 728 real-world prompts across four major genres (Argumentative, Narrative, Descriptive, and Expository), and includes both Open-Ended and Constrained types. Our evaluation protocol is validated through a comprehensive human agreement study. The results show that our protocol aligns well with human judgments, achieving a highest Spearman's correlation of 0.816 and outperforming coarse-grained evaluation methods by an average of 8.6\%. Finally, we benchmark 15 large LLMs, analyzing their strengths and limitations across genres and instruction types. We believe EssayBench offers a more reliable framework for evaluating Chinese essay generation and provides valuable insights for improving LLMs in this domain.

PDF Details DOI

TMLR Journal 2026 Journal Article

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs

Jierun Chen
Tiezheng Yu
Haoli Bai
Lewei Yao
Jiannan Wu
Kaican Li
Fei Mi
Chaofan Tao

Large vision-language models (VLMs) increasingly adopt post-training techniques such as long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL) to elicit sophisticated reasoning. While these methods exhibit synergy in language-only models, their joint effectiveness in VLMs remains uncertain. We present a systematic investigation into the distinct roles and interplay of long-CoT SFT and RL across multiple multimodal reasoning benchmarks. We find that SFT improves performance on difficult questions by in-depth, structured reasoning, but introduces verbosity and degrades performance on simpler ones. In contrast, RL promotes generalization and brevity, yielding consistent improvements across all difficulty levels, though the improvements on the hardest questions are less prominent compared to SFT. Surprisingly, combining them through two-staged, interleaved, or progressive training strategies, as well as data mixing and model merging, all fails to produce additive benefits, instead leading to trade-offs in accuracy, reasoning style, and response length. This "synergy dilemma" highlights the need for more seamless and adaptive approaches to unlock the full potential of combined post-training techniques for reasoning VLMs. Code, dataset, and fine-tuned models are available at https://github.com/JierunChen/SFT-RL-SynergyDilemma.

PDF Details

ICLR Conference 2024 Conference Paper

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis

Kai Chen 0023
Chunwei Wang
Kuo Yang
Jianhua Han
Lanqing Hong
Fei Mi
Hang Xu 0004
Zhengying Liu

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content, either unintentionally or because of intentional inducement. Existing alignment methods usually direct LLMs toward the favorable outcomes by utilizing human-annotated, flawless instruction-response pairs. Conversely, this study proposes a novel alignment technique based on mistake analysis, which deliberately exposes LLMs to erroneous content to learn the reasons for mistakes and how to avoid them. In this case, mistakes are repurposed into valuable data for alignment, effectively helping to avoid the production of erroneous responses. Without external models or human annotations, our method leverages a model's intrinsic ability to discern undesirable mistakes and improves the safety of its generated responses. Experimental results reveal that our method outperforms existing alignment approaches in enhancing model safety while maintaining the overall utility.

Details

AAAI Conference 2023 Conference Paper

KPT: Keyword-Guided Pre-training for Grounded Dialog Generation

Qi Zhu
Fei Mi
Zheng Zhang
Yasheng Wang
Yitong Li
Xin Jiang
Qun Liu
Xiaoyan Zhu

Incorporating external knowledge into the response generation process is essential to building more helpful and reliable dialog agents. However, collecting knowledge-grounded conversations is often costly, calling for a better pre-trained model for grounded dialog generation that generalizes well w.r.t. different types of knowledge. In this work, we propose KPT (Keyword-guided Pre-Training), a novel self-supervised pre-training method for grounded dialog generation without relying on extra knowledge annotation. Specifically, we use a pre-trained language model to extract the most uncertain tokens in the dialog as keywords. With these keywords, we construct two kinds of knowledge and pre-train a knowledge-grounded response generation model, aiming at handling two different scenarios: (1) the knowledge should be faithfully grounded; (2) it can be selectively used. For the former, the grounding knowledge consists of keywords extracted from the response. For the latter, the grounding knowledge is additionally augmented with keywords extracted from other utterances in the same dialog. Since the knowledge is extracted from the dialog itself, KPT can be easily performed on a large volume and variety of dialogue data. We considered three data sources (open-domain, task-oriented, conversational QA) with a total of 2.5M dialogues. We conduct extensive experiments on various few-shot knowledge-grounded generation tasks, including grounding on dialog acts, knowledge graphs, persona descriptions, and Wikipedia passages. Our comprehensive experiments and analyses demonstrate that KPT consistently outperforms state-of-the-art methods on these tasks with diverse grounding knowledge.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

Bin Sun
Yitong Li
Fei Mi
Weichao Wang
Yiwei Li
Kan Li

Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that continuous latent variables tend to reduce the coherence of generated responses. In this paper, we also found that discrete latent variables have difficulty capturing more diverse expressions. To tackle these problems, we combine the merits of both continuous and discrete latent variables and propose a Hybrid Latent Variable (HLV) method. Specifically, HLV constrains the global semantics of responses through discrete latent variables and enriches responses with continuous latent variables. Thus, we diversify the generated responses while maintaining relevance and coherence. In addition, we propose Conditional Hybrid Variational Transformer (CHVT) to construct and to utilize HLV with transformers for dialogue generation. Through fine-grained symbolic-level semantic information and additive Gaussian mixing, we construct the distribution of continuous variables, prompting the generation of diverse expressions. Meanwhile, to maintain the relevance and coherence, the discrete latent variable is optimized by self-separation training. Experimental results on two dialogue generation datasets (DailyDialog and Opensubtitles) show that CHVT is superior to traditional transformer-based variational mechanism w.r.t. diversity, relevance and coherence metrics. Moreover, we also demonstrate the benefit of applying HLV to fine-tuning two pre-trained dialogue models (PLATO and BART-base).

PDF Details DOI

AAAI Conference 2022 Conference Paper

CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog Systems

Fei Mi
Yasheng Wang
Yitong Li

As the labeling cost for different modules in task-oriented dialog (ToD) systems is high, a major challenge is to learn different tasks with the least amount of labeled data. Recently, pre-trained language models (PLMs) have shown promising results for few-shot learning in ToD. To better utilize the power of PLMs, this paper proposes Comprehensive Instruction (CINS) that exploits PLMs with extra taskspecific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD, ie. intent classification, dialog state tracking, and natural language generation. A sequence-to-sequence model (T5) is adopted to solve these three tasks in a unified framework. Extensive experiments are conducted on these ToD tasks in realistic fewshot learning scenarios with small validation data. Empirical results demonstrate that the proposed CINS approach consistently improves techniques that finetune PLMs with raw input or short prompt.

PDF Details

IJCAI Conference 2020 Conference Paper

Memory Augmented Neural Model for Incremental Session-based Recommendation

Fei Mi
Boi Faltings

Increasing concerns with privacy have stimulated interests in Session-based Recommendation (SR) using no personal data other than what is observed in the current browser session. Existing methods are evaluated in static settings which rarely occur in real-world applications. To better address the dynamic nature of SR tasks, we study an incremental SR scenario, where new items and preferences appear continuously. We show that existing neural recommenders can be used in incremental SR scenarios with small incremental updates to alleviate computation overhead and catastrophic forgetting. More importantly, we propose a general framework called Memory Augmented Neural model (MAN). MAN augments a base neural recommender with a continuously queried and updated nonparametric memory, and the predictions from the neural and the memory components are combined through another lightweight gating network. We empirically show that MAN is well-suited for the incremental SR task, and it consistently outperforms state-oft-he-art neural and nonparametric methods. We analyze the results and demonstrate that it is particularly good at incrementally learning preferences on new and infrequent items.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems

Fei Mi
Minlie Huang
Jiyong Zhang
Boi Faltings

Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta tasks, and directly incorporates the objective of adapting to new low-resource NLG tasks into the meta-learning optimization process. Extensive experiments are conducted on a large multi-domain dataset (MultiWoz) with diverse linguistic variations. We show that Meta-NLG significantly outperforms other training procedures in various low-resource configurations. We analyze the results, and demonstrate that Meta-NLG adapts extremely fast and well to low-resource situations.

PDF Details

IJCAI Conference 2016 Conference Paper

Adaptive Sequential Recommendation Using Context Trees

Fei Mi
Boi Faltings

Machine learning is often used to acquire knowledge in domains that undergo frequent changes, such as networks, social media, or markets. These frequent changes poses a challenge to most machine learning methods as they have difficulty adapting. So my thesis topic focus on adaptive machine learning models. At the first step, we consider a forum content recommender system for massive open online courses (MOOCs) as an example of an application where recommendations have to adapt to new items and evolving user preferences. We formalize the recommendation problem as a sequence prediction problem and compare different recommendation methods, including a new method called context tree (CT). The results show that the CT recommender performs much better than other methods. We analyze the reasons for this and demonstrate that it is because of better adaptation to changes in the domain.

PDF Details

AAAI Conference 2015 Conference Paper

Probabilistic Graphical Models for Boosting Cardinal and Ordinal Peer Grading in MOOCs

Fei Mi
Dit-Yan Yeung

With the enormous scale of massive open online courses (MOOCs), peer grading is vital for addressing the assessment challenge for open-ended assignments or exams while at the same time providing students with an effective learning experience through involvement in the grading process. Most existing MOOC platforms use simple schemes for aggregating peer grades, e. g. , taking the median or mean. To enhance these schemes, some recent research attempts have developed machine learning methods under either the cardinal setting (for absolute judgment) or the ordinal setting (for relative judgment). In this paper, we seek to study both cardinal and ordinal aspects of peer grading within a common framework. First, we propose novel extensions to some existing probabilistic graphical models for cardinal peer grading. Not only do these extensions give superior performance in cardinal evaluation, but they also outperform conventional ordinal models in ordinal evaluation. Next, we combine cardinal and ordinal models by augmenting ordinal models with cardinal predictions as prior. Such combination can achieve further performance boosts in both cardinal and ordinal evaluations, suggesting a new research direction to pursue for peer grading on MOOCs. Extensive experiments have been conducted using real peer grading data from a course called “Science, Technology, and Society in China I” offered by HKUST on the Coursera platform.

PDF Details