Papers by Lili Mou
Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Sentence summarization systems that use latent space to reconstruct the source sentence are unwillingly exploited. |
| Approach: | They propose a method that uses language modeling and semantic similarity metrics to find a high-scoring summary. |
| Outcome: | The proposed method achieves state-of-the-art for unsupervised sentence summarization according to ROUGE scores. |
IntentCoding: Amplifying User Intent in Code Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | IntentCoding captures the influence of user intent by masking out the intent, and integrates seamlessly with existing decoding procedures. |
| Approach: | They propose a decoding strategy that captures the influence of user intent by masking out the intent and applies a multi-strength ensemble mechanism to amplify the effect of user intention during generation. |
| Outcome: | The proposed model significantly improves both constraint satisfaction and functional correctness compared to greedy decoding approaches. |
Seq2Emo: A Sequence to Multi-Label Emotion Classification Model (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for multi-label emotion classification are based on binary relevance and classifier chain (CC) |
| Approach: | They propose a sequence-to-emotion approach which implicitly models emotion correlations in a bi-directional decoder. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on a SemEval’18 and GoEmotions dataset. |
Discreteness in Neural Natural Language Processing (D19-2)
Copied to clipboard
| Challenge: | This tutorial provides a comprehensive guide to the process of discreteness in neural NLP. |
| Approach: | This tutorial provides a comprehensive guide to the process of discreteness in neural NLP. |
| Outcome: | This tutorial explains the process of discreteness in neural NLP. |
Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization (2022.acl-long)
Copied to clipboard
| Challenge: | Text summarization aims to generate a short summary for an input text. |
| Approach: | They propose a non-autoregressive unsupervised summarization approach which performs edit-based search towards a heuristicically defined score and generates a summary as pseudo-groundtruth. |
| Outcome: | The proposed approach achieves state-of-the-art performance for unsupervised summarization, while improving inference efficiency. |
Adversarial Learning on the Latent Space for Diverse Dialog Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for dialog generation generate generic utterances, e.g., always generating "I don't know" |
| Approach: | They propose a framework that uses generative adversarial nets to generate conditioned responses in dialogs. |
| Outcome: | The proposed model generates more fluent, relevant, and diverse responses than state-of-the-art methods. |
Document-Level Relation Extraction with Sentences Importance Estimation and Focusing (2022.naacl-main)
Copied to clipboard
| Challenge: | Document-level relation extraction models are not robust and exhibit bizarre behaviors when non-evidence sentences are removed. |
| Approach: | They propose a document-level relation extraction framework that uses a sentence importance score and a focusing loss to encourage DocRE models to focus on evidence sentences. |
| Outcome: | The proposed framework improves overall performance and makes DocRE models more robust. |
Generating Sentences from Disentangled Syntactic and Semantic Spaces (P19-1)
Copied to clipboard
| Challenge: | Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. |
| Approach: | They propose to generate sentences from disentangled syntactic and semantic spaces by using the linearized tree sequence. |
| Outcome: | The proposed method achieves similar or better performance in various tasks compared with state-of-the-art models. |
KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Empirical evaluation shows that our approach yields superior performance in both standard task metrics and large language model (LLM)-based evaluation. |
| Approach: | They propose a K-step return estimation method for reinforcement learning (RL)-based knowledge distillation in text generation tasks using the Bellman Optimality Equation. |
| Outcome: | The proposed method performs better on standard task metrics and large language model evaluations on three text generation tasks. |
Unsupervised Paraphrasing by Simulated Annealing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to generate accurate and different-appearing paraphrases require massive parallel samples for training. |
| Approach: | They propose a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing by performing local editing. |
| Outcome: | The proposed approach outperforms existing models in automatic and human evaluations on Quora, Wikianswers, MSCOCO, and Twitter. |
A Dual-View Approach to Classifying Radiology Reports by Co-Training (2024.lrec-main)
Copied to clipboard
| Challenge: | Using the structure of a radiology report, we propose a co-training approach to train two machine learning models using the dual views of MRI and CT data. |
| Approach: | They propose a co-training approach where two machine learning models are built upon the Findings and Impression sections and use each other's information to boost performance with massive unlabeled data in a semi-supervised manner. |
| Outcome: | The proposed model outperforms supervised and semi-supervised methods in a public health surveillance study and outperformed existing methods. |
Disentangled Representation Learning for Non-Parallel Text Style Transfer (P19-1)
Copied to clipboard
| Challenge: | a paper aims to disentangle latent representations of style and content in language models . auxiliary multi-task and adversarial objectives are used to disentangle the latent space . |
| Approach: | They propose a simple yet effective approach to disentangling latent representations . they propose auxiliary multi-task and adversarial objectives to disentangle style and content . |
| Outcome: | The proposed approach achieves high performance in terms of transfer accuracy, content preservation, and language fluency compared to previous approaches . |
Multi-Persona Thinking for Bias Mitigation in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. |
| Approach: | They propose a simple inference-time framework that encourages reasoning from multiple perspectives. |
| Outcome: | The proposed framework reduces bias by encouraging reasoning from multiple perspectives. |
An Imitation Learning Approach to Unsupervised Parsing (P19-1)
Copied to clipboard
| Challenge: | Unsupervised parsing is a form of reinforcement learning that improves syntactic structures but lacks interpretability due to its lack of ad hoc heuristics. |
| Approach: | They propose an unsupervised approach that transfers syntactic knowledge to a Tree-LSTM model with discrete parsing actions. |
| Outcome: | The proposed model outperforms existing models on the All Natural Language Inference dataset and achieves a new state of the art in terms of parsing F-score. |
Iterative Edit-Based Unsupervised Sentence Simplification (2020.acl-main)
Copied to clipboard
| Challenge: | Sentence simplification is relevant in various real-world and downstream applications. |
| Approach: | They propose an edit-based approach to unsupervised sentence simplification that uses a scoring function to score fluency, simplicity, and meaning preservation to perform edits. |
| Outcome: | The proposed model is more controllable and interpretable than state-of-the-art models on newsela and WikiLarge datasets. |
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that the latent space learned by WAE exhibits properties of continuity and smoothness as in VAEs. |
| Approach: | They propose to use the variational autoencoder (VAE) for probabilistic sentence generation . they propose a variant of WAE that encourages the stochasticity of the encoder . |
| Outcome: | The proposed variant encourages the stochasticity of the encoder while achieving higher BLEU scores. |
Prompt-Based Editing for Text Style Transfer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Text style transfer is a type of textual prompt that generates style-transferred texts word by word . early prediction errors may affect future word predictions. |
| Approach: | They propose a prompt-based editing approach to text style transfer using a pretrained language model. |
| Outcome: | The proposed approach outperforms existing systems with 20 times more parameters on three style-transfer benchmark datasets. |
Claim-Centric and Sentiment Guided Graph Attention Network for Rumour Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Social media exerts a substantial influence on individuals' day-to-day existence, a new study shows . the rapid propagation of false information and fake news is a critical aspect of rumour detection . |
| Approach: | They propose a model that takes into account the claim in the source tweet and includes tweet sentiment along with the propagation graph. |
| Outcome: | The proposed model outperforms existing models and improves on sentiment labels. |
Harnessing Pre-Trained Neural Networks with Rules for Formality Style Transfer (D19-1)
Copied to clipboard
| Challenge: | Existing studies normalize informal sentences with rules, but they introduce noise if we use them in a naive way. |
| Approach: | They propose to harness rules into a state-of-the-art neural network that is typically pretrained on massive corpora. |
| Outcome: | The proposed method can be used to generate a state-of-the-art on a small dataset. |
Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for predicting linguistic structures require labeled data . unsupervised chunking is useful for understanding linguistic structure of human languages . |
| Approach: | They propose a knowledge-transfer approach that heuristically induces chunk labels from unsupervised parsing models and a hierarchical recurrent neural network (HRNN) they show that their approach bridges the gap between supervised and unsupervised chunking. |
| Outcome: | The proposed method bridges the gap between supervised and unsupervised chunking. |
Ultra-Low-Dimensional Prompt Tuning via Random Projection (2026.eacl-long)
Copied to clipboard
| Challenge: | Prompt tuning addresses parameter-efficiency by learning embeddings, but these embeddements are typically tied to the model’s hidden dimensionality, limiting parameter saving. |
| Approach: | They propose a parameter-efficient method that learns prompt embeddings exclusively in the input layer of the model and uses a frozen random matrix for up-projection. |
| Outcome: | The proposed method outperforms previous methods using significantly fewer parameters while maintaining performance. |
Formality Style Transfer with Shared Latent Space (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches for formality style transfer use neural networks for sentence generation, but the dataset for formal style transfer is considerably smaller than translation corpora. |
| Approach: | They propose a new approach for formality style transfer using shared latent space and two auxiliary losses. |
| Outcome: | The proposed approach outperforms baselines in various settings, especially when limited data is available. |
Variational Attention for Sequence-to-Sequence Models (C18-1)
Copied to clipboard
| Challenge: | Existing variational autoencoders encode data to latent variables and then decode them into target data. |
| Approach: | They propose a variational attention mechanism where the attention vector is also modeled as Gaussian distributed random variables. |
| Outcome: | The proposed method reduces the variational latent space bypassing phenomenon as it increases diversity of generated sentences. |
LLMR: Knowledge Distillation with a Large Language Model-Induced Reward (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models have demonstrated remarkable performance in various NLP tasks, but are typically computationally expensive and difficult to be deployed in resource-constrained environments. |
| Approach: | They propose a knowledge distillation method based on a reward function induced from large language models. |
| Outcome: | The proposed method outperforms traditional methods on multiple datasets and tasks. |
f-Divergence Minimization for Sequence-Level Knowledge Distillation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge distillation approaches focus on minimizing a generalized f-divergence function. |
| Approach: | They propose a framework which formulates sequence-level knowledge distillation as minimizing a generalized f-divergence function. |
| Outcome: | The proposed framework outperforms existing methods and reduces intractable divergence to word-level losses. |
Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models (L18-1)
Copied to clipboard
| Challenge: | Existing methods for speaker modeling are based on hand-crafted statistics and ad hoc to a certain application. |
| Approach: | They propose to use speaker classification as a surrogate task for general speaker modeling and collect massive data to facilitate research in this direction. |
| Outcome: | The proposed models outperform the existing models and are feasible with speaker identity information. |
VEG: Verbal 𝜖-greedy for Semantic Exploration in Multi-Turn RL Agents (2026.acl-industry)
Copied to clipboard
Yongchang Hao, Jie Hao, Yongsheng Mei, Ze Ye, Junyi Chai, Bin Guo, Benjamin Z. Yao, Chenlei Guo, Lili Mou
| Challenge: | Standard RL approaches suffer from reward sparsity and mode-seeking behavior . lack of diversity hinders exploration necessary for optimal learning . |
| Approach: | They propose a framework that leverages external feedback as a dynamic control variable to explicitly balance exploration and exploitation within the semantic space. |
| Outcome: | Experiments on Tau Bench and SearchQA show that the proposed framework outperforms standard RL baselines. |
Improving Word Sense Disambiguation with Translations (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing WSD systems rarely consider multilingual information for word sense disambiguation (WSD). |
| Approach: | They propose a method that leverages multilingual information to improve a base WSD system by generating translations. |
| Outcome: | The proposed method improves performance of a base WSD system in English and multilingual WSD on several languages. |
Stylized Text Generation: Approaches and Applications (2020.acl-tutorials)
Copied to clipboard
| Challenge: | Text generation has played an important role in various applications of natural language processing. |
| Approach: | They present different settings of stylized text generation and introduce machine learning methods to represent style. |
| Outcome: | This paper presents a comprehensive literature review on stylized text generation . it focuses on the challenges and future directions of stylized generation based on machine learning . |
An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing benchmark datasets for open-domain dialogue generation are advancing the field . overlapping between training and test sets can cause fake performance . |
| Approach: | They analyze dailyDialog and OpenSubtitles to find out how overlapping can be exploited to obtain fake state-of-the-art performance. |
| Outcome: | The proposed datasets are cleaned and set up for future research. |
A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for length control summarization treat the length requirement as a soft constraint, which may not always be satisfied. |
| Approach: | They propose a novel length-control decoding algorithm based on the directed acyclic Transformer (DAT) their approach allows for multiple plausible sequence fragments and predicts a path to connect them. |
| Outcome: | The proposed algorithm allows for multiple plausible sequence fragments and predicts a path to connect them. |
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)
Copied to clipboard
Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li
| Challenge: | Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). |
| Approach: | They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities. |
| Outcome: | The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks. |
Knowledge Distillation for Language Models (2025.naacl-tutorial)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) aims to transfer knowledge from a teacher to a student . this tutorial will cover topics ranging from LLM sequence compression to LLM self-distillation . |
| Approach: | They propose to introduce intermediate-layer matching and prediction matching . they will then present advanced techniques such as reinforcement learning-based KD and multi-teacher distillation . |
| Outcome: | This tutorial aims to provide participants with a comprehensive understanding of the techniques and applications of knowledge distillation for language models. |