Author name cluster

Chen Ma 0001

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.

6 papers

1 author row

ICLR Conference 2025 Conference Paper

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

Bowei He
Lihao Yin
Hui-Ling Zhen
Jianping Zhang 0002
Lanqing Hong
Mingxuan Yuan
Chen Ma 0001

The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications, as they can stealthily affect multiple downstream tasks. While certifying robustness against such threats is crucial, existing defenses struggle with the high-dimensional, interdependent nature of textual data and the lack of access to original poisoned pre-training data. To address these challenges, we introduce **F**uzzed **R**andomized **S**moothing (**FRS**), a novel approach for efficiently certifying language model robustness against backdoor attacks. FRS integrates software robustness certification techniques with biphased model parameter smoothing, employing Monte Carlo tree search for proactive fuzzing to identify vulnerable textual segments within the Damerau-Levenshtein space. This allows for targeted and efficient text randomization, while eliminating the need for access to poisoned training data during model smoothing. Our theoretical analysis demonstrates that FRS achieves a broader certified robustness radius compared to existing methods. Extensive experiments across various datasets, model configurations, and attack strategies validate FRS's superiority in terms of defense efficiency, accuracy, and robustness.

Details

ICLR Conference 2025 Conference Paper

Decision Information Meets Large Language Models: The Future of Explainable Operations Research

Yansen Zhang
Qingcan Kang
Wing Yin Yu
Hailei Gong
Xiaojin Fu
Xiongwei Han
Tao Zhong 0004
Chen Ma 0001

Operations Research (OR) is vital for decision-making in many industries. While recent OR methods have seen significant improvements in automation and efficiency through integrating Large Language Models (LLMs), they still struggle to produce meaningful explanations. This lack of clarity raises concerns about transparency and trustworthiness in OR applications. To address these challenges, we propose a comprehensive framework, Explainable Operations Research (EOR), emphasizing actionable and understandable explanations accompanying optimization. The core of EOR is the concept of Decision Information, which emerges from what-if analysis and focuses on evaluating the impact of complex constraints (or parameters) changes on decision-making. Specifically, we utilize bipartite graphs to quantify the changes in the OR model and adopt LLMs to improve the explanation capabilities. Additionally, we introduce the first industrial benchmark to rigorously evaluate the effectiveness of explanations and analyses in OR, establishing a new standard for transparency and clarity in the field.

Details

ICML Conference 2025 Conference Paper

Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency

Zexu Sun
Qiyu Han
Hao Yang 0045
Anpeng Wu
Minqin Zhu
Dugang Liu
Chen Ma 0001
Yunpeng Weng

In online platforms, incentives ( e. g. , discounts, coupons) are used to boost user engagement and revenue. Uplift modeling methods are developed to estimate user responses from observational data, often incorporating distribution balancing to address selection bias. However, these methods are limited by in-distribution testing data, which mirrors the training data distribution. In reality, user features change continuously due to time, geography, and other factors, especially on complex online marketing platforms. Thus, effective uplift modeling method for out-of-distribution data is crucial. To address this, we propose a novel uplift modeling method I nvariant D eep U plift M odeling, namely IDUM, which uses invariant learning to enhance out-of-distribution generalization by identifying causal factors that remain consistent across domains. IDUM further refines these features into necessary and sufficient factors and employs a masking component to reduce computational costs by selecting the most informative invariant features. A balancing discrepancy component is also introduced to mitigate selection bias in observational data. We conduct extensive experiments on public and real-world datasets to demonstrate IDUM’s effectiveness in both in-distribution and out-of-distribution scenarios in online marketing. Furthermore, we also provide theoretical analysis and related proofs to support our IDUM’s generalizability.

Details

ICLR Conference 2025 Conference Paper

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

Qiyuan Zhang 0001
Yufei Wang 0005
Tiezheng Yu
Yuxin Jiang
Chuhan Wu
Liangyou Li
Yasheng Wang
Xin Jiang 0002

With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing text generation quality in a wide range of tasks. However, there still remains a reliability gap between LLM-as-a-Judge and human evaluation. One important reason is the lack of guided oracles in the evaluation process. Motivated by the role of reference pervasively used in classic text evaluation, we introduce RevisEval, a novel text generation evaluation paradigm via the response-adapted references. RevisEval is driven by the key observation that an ideal reference should maintain the necessary relevance to the response to be evaluated. Specifically, RevisEval leverages the text revision capabilities of large language models (LLMs) to adaptively revise the response, then treat the revised text as the reference (response-adapted reference) for the subsequent evaluation. Extensive experiments demonstrate that RevisEval outperforms traditional reference-free and reference-based evaluation paradigms that use LLM-as-a-Judge across NLG tasks and open-ended instruction-following tasks. More importantly, our response-adapted references can further boost the classical text metrics, e.g., BLEU and BERTScore, compared to traditional references and even rival the LLM-as-a-Judge. A detailed analysis is also conducted to confirm RevisEval's effectiveness in bias reduction, the impact of inference cost, and reference relevance.

Details

ICLR Conference 2024 Conference Paper

Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation

Chengming Hu
Haolun Wu
Xuan Li
Chen Ma 0001
Xi Chen 0009
Boyu Wang 0004
Jun Yan 0007
Xue Liu 0001

Knowledge distillation aims to train a compact student network using soft supervision from a larger teacher network and hard supervision from ground truths. However, determining an optimal knowledge fusion ratio that balances these supervisory signals remains challenging. Prior methods generally resort to a constant or heuristic-based fusion ratio, which often falls short of a proper balance. In this study, we introduce a novel adaptive method for learning a sample-wise knowledge fusion ratio, exploiting both the correctness of teacher and student, as well as how well the student mimics the teacher on each sample. Our method naturally leads to the \textit{intra-sample} trilateral geometric relations among the student prediction ($\mathcal{S}$), teacher prediction ($\mathcal{T}$), and ground truth ($\mathcal{G}$). To counterbalance the impact of outliers, we further extend to the \textit{inter-sample} relations, incorporating the teacher's global average prediction ($\mathcal{\bar{T}})$ for samples within the same class. A simple neural network then learns the implicit mapping from the intra- and inter-sample relations to an adaptive, sample-wise knowledge fusion ratio in a bilevel-optimization manner. Our approach provides a simple, practical, and adaptable solution for knowledge distillation that can be employed across various architectures and model sizes. Extensive experiments demonstrate consistent improvements over other loss re-weighting methods on image classification, attack detection, and click-through rate prediction.

Details

UAI Conference 2023 Conference Paper

MMEL: A Joint Learning Framework for Multi-Mention Entity Linking

Chengmei Yang
Bowei He
Yimeng Wu
Chao Xing
Lianghua He
Chen Ma 0001

Entity linking, bridging mentions in the contexts with their corresponding entities in the knowledge bases, has attracted wide attention due to many potential applications. Recently, plenty of multimodal entity linking approaches have been proposed to take full advantage of the visual information rather than solely the textual modality. Although feasible, these methods mainly focus on the single-mention scenarios and neglect the scenarios where multiple mentions exist simultaneously in the same context, which limits the performance. In fact, such multi-mention scenarios are pretty common in public datasets and real-world applications. To solve this challenge, we first propose a joint feature extraction module to learn the representations of context and entity candidates, from both the visual and textual perspectives. Then, we design a pairwise training scheme (for training) and a multi-mention collaborative ranking method (for testing) to model the potential connections between different mentions. We evaluate our method on a public dataset and a self-constructed dataset, NYTimes-MEL, under both text-only and multimodal scenarios. The experimental results demonstrate that our method can largely outperform the state-of-the-art methods, especially in multi-mention scenarios. Our dataset and source code are publicly available at https: //github. com/ycm094/MMEL-main.

Details