Papers by Jing Qian
The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to enhance an LLM's privacy awareness with thousands of samples decrease its fairness awareness. |
| Approach: | They propose a training-free method to Suppress the Privacy and faIrness coupled Neurons (SPIN) which theoretically and empirically decreases the mutual information between fairness and privacy awareness. |
| Outcome: | The proposed method reduces the mutual information between fairness and privacy awareness without compromising general capabilities. |
Language Model Detoxification in Dialogue with Contextualized Stance Control (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on Language Model detoxification has focused on reducing the toxicity of the generation itself without consideration of the context. |
| Approach: | They propose a method to do context-dependent detoxification without taking into account the stance of the generated response. |
| Outcome: | The proposed method can learn the context-dependent stance control strategies while keeping a low self-toxicity of the underlying LM. |
Exploring Mode Connectivity for Pre-trained Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found. |
| Approach: | They investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path. |
| Outcome: | The proposed model can be used to find low-loss paths between two minima, and to understand how their mode connectivity affects their task knowledge. |
ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models with long chain-of-thought reasoning lack reasoning depth and domain-specific utility. |
| Approach: | They propose a model merging framework that integrates reasoning with domain-specific task models. |
| Outcome: | The proposed model merging framework outperforms state-of-the-art models while maintaining robust reasoning performance. |
LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models for specialized tasks are costly and time-consuming. |
| Approach: | They propose a framework that locates task-specific neurons via gradient-based attribution and dynamically Elects critical neurons through multi-model importance fusion. |
| Outcome: | The proposed framework reduces harmful response rates while preserving 95% of utility performance. |
Learning to Decipher Hate Symbols (N19-1)
Copied to clipboard
| Challenge: | Existing computational models of hate speech focus on a binary or multiclass classification task . a recent study shows an alarming 4.6% increase in hate speech in 2016 . |
| Approach: | They propose a task of deciphering hate symbols using the Urban Dictionary . they propose ciphers using Sequence-to-Sequence models and a Variational Decipher . |
| Outcome: | The proposed model can crack hate symbols based on context and generalize better to unseen symbols in a more challenging testing setting. |
Limitations of Language Models in Arithmetic and Symbolic Induction (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown that large pretrained Language Models (LMs) can perform remarkably well on a range of NLP tasks but they have limitations on basic symbolic manipulation tasks such as copy, reverse, and addition. |
| Approach: | They propose to use explicit positional markers, fine-grained computation steps, and LMs with callable programs to teach large pretrained Language Models. |
| Outcome: | The proposed model can perform 100% accuracy in OOD and repeating symbols. |
Towards Understanding Gender Bias in Relation Extraction (2020.acl-main)
Copied to clipboard
Andrew Gaut, Tony Sun, Shirlyn Tang, Yuxin Huang, Jing Qian, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, William Yang Wang
| Challenge: | Existing bias mitigation techniques have a negative effect on NRE, a study finds . |
| Approach: | They create a dataset to analyze gender bias in relation extraction systems . they find that existing bias mitigation techniques have a negative effect on NRE . |
| Outcome: | The proposed dataset analyzes gender bias in relation extraction systems using a 10% human annotated test set. |
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on pre-trained LLMs to better understand and improve their trustworthiness. |
| Approach: | They apply linear probing to LLMs to explore five key dimensions of trustworthiness: reliability, privacy, toxicity, fairness, and robustness. |
| Outcome: | The proposed model can distinguish concepts in each trustworthiness dimension, suggesting that it can be trained in early pre-training. |
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)
Copied to clipboard
Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang
| Challenge: | Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). |
| Approach: | a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance. |
| Outcome: | a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models . |
FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding (2022.acl-long)
Copied to clipboard
Yanan Zheng, Jing Zhou, Yujie Qian, Ming Ding, Chonghua Liao, Li Jian, Ruslan Salakhutdinov, Jie Tang, Sebastian Ruder, Zhilin Yang
| Challenge: | Existing evaluation protocols for few-shot natural language understanding (NLU) tasks are inconsistent and hinder fair comparison and measuring progress. |
| Approach: | They propose an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability. |
| Outcome: | The proposed framework improves evaluation procedures in three key aspects, i.e., performance, dev-test correlation, and stability. |
Controllable Natural Language Generation with Contrastive Prefixes (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing work on controllable natural language generation has focused on fine-tuning existing models or using attribute discriminators. |
| Approach: | They propose a lightweight framework for controllable GPT2 generation that utilizes attribute-specific vectors to steer natural language generation. |
| Outcome: | The proposed framework can guide generation towards desired attributes while keeping high linguistic quality. |
A Survey on Natural Language Processing for Fake News Detection (2020.lrec-1)
Copied to clipboard
| Challenge: | Automated fake news detection is a critical but challenging problem in NLP . social media has accelerated the spread of fake news, threatening public safety . |
| Approach: | They describe the challenges involved in fake news detection and describe related tasks . they outline promising research directions and highlight the difference between fake news and related tasks. |
| Outcome: | The proposed models are more fine-grained, detailed, fair, and practical. |
Memformer: A Memory-Augmented Transformer for Sequence Modeling (2022.findings-aacl)
Copied to clipboard
| Challenge: | Experimental results show that Memformer uses 8.1x less memory space and 3.2x faster on inference. |
| Approach: | They propose an efficient neural network that utilizes an external dynamic memory to encode and retrieve past information. |
| Outcome: | The proposed model achieves comparable performance against baselines with 8.1x less memory space and 3.2x faster on inference. |
Controllable Dialogue Simulation with In-context Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to generate annotated dialogues require crowdsourcing, which is expensive and time-consuming. |
| Approach: | They propose a dialogue simulation method based on large language model in-context learning that generates new dialogues and annotations in a controllable way. |
| Outcome: | The proposed method can expand a small set of dialogue data with minimum or zero human involvement and parameter update. |
Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection (N18-2)
Copied to clipboard
| Challenge: | Existing methods that focus on a single tweet as input are likely to yield high false positive and negative rates. |
| Approach: | They propose a model that leverages intra-user and inter-user representation learning to improve hate speech detection on Twitter by suppressing the noise in a single Tweet. |
| Outcome: | The proposed model significantly improves the f-score of a strong bidirectional LSTM model by 10.1%. |
Hierarchical CVAE for Fine-Grained Hate Speech Classification (D18-1)
Copied to clipboard
| Challenge: | Existing work on automated hate speech detection focuses on binary classification or on differentiating among a small set of categories. |
| Approach: | They propose a method to discriminate among 40 hate groups of 13 different hate group categories. |
| Outcome: | The proposed method outperforms discriminative models on a fine-grained hate speech classification task. |
Lifelong Learning of Hate Speech Classification on Social Media (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing work on automated hate speech classification assumes that the dataset is fixed and the classes are pre-defined. |
| Approach: | They propose to use Variational Representation Learning and a load-balancing self-organizing inductive neural network to learn hate speech classification on social media. |
| Outcome: | The proposed model improves on the lifelong learning techniques on social media. |
A Benchmark Dataset for Learning to Intervene in Online Hate Speech (D19-1)
Copied to clipboard
| Challenge: | Existing methods to detect online hate speech ignore conversational context . generative hate speech intervention is a novel approach to counter online hate . |
| Approach: | They propose a task where generative hate speech intervention generates responses to intervene during online conversations that contain hate speech. |
| Outcome: | The proposed method can detect and block hate speech and discourage it . it can also generate responses written by Mechanical Turk workers . |
Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)
Copied to clipboard
Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu
| Challenge: | Recent VSE models combine simple pooling methods with hard triplet loss to improve performance. |
| Approach: | They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods. |
| Outcome: | The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval. |
Equal Truth: Rumor Detection with Invariant Group Fairness (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing rumor detection methods rarely consider fairness issues inherent in the model . this can lead to biased predictions across stakeholder groups, undermining their detection effectiveness . |
| Approach: | They propose a framework to address fairness issues inherent in rumor detection models . they perform unsupervised partitioning to dynamically identify potential unfair data patterns . then, they apply invariant learning to these partitions to extract fair and informative feature representations . |
| Outcome: | The proposed method outperforms strong baselines regarding detection and fairness performance . it also shows robust performance on out-of-distribution samples . |
Fine-grained Entity Typing without Knowledge Base (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on fine-grained entity typing (FET) relies on knowledge bases as distant supervision, but lack of or incompleteness of KB can hinder training. |
| Approach: | They propose a two-step framework that trains FET models without accessing any knowledge base. |
| Outcome: | The proposed framework achieves competitive performance with respect to the models trained on the original KB-supervised datasets. |