Papers by Chunyuan Li

24 papers
Adaptive Hyper-parameter Learning for Deep Semantic Retrieval (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for deep semantic retrieval are highly sensitive to hyper-parameters . a novel adaptive metric learning method is proposed to overcome this limitation .
Approach: They propose a method that adaptively obtains hyper-parameters without fixed or extra-trainable hyper-parmeters . they adopt a symmetric metric learning method to mitigate model collapse issues .
Outcome: The proposed method outperforms existing methods on a real-world dataset and brings economic benefits.
Rethinking Sentiment Style Transfer (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation methods for text style transfer are unsatisfactory.
Approach: They propose to use a graph-based method to extract attribute content from sentences . they propose an efficient regularization to leverage attribute-dependent content as guiding signals.
Outcome: The proposed method is based on a YELP and IMDB dataset and it is able to detect errors in the human evaluation.
ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit remarkable adaptability across domains, but they are often not suitable for structured knowledge extraction tasks such as named entity recognition (NER).
Approach: They propose a method that instructs LLMs to self-reflect on the specific domain and generates domain-relevant attributes for creating attribute-rich training data.
Outcome: The proposed method produces NER datasets in domains with domain-relevant attributes and generates entity terms and NER context data around these entities.
Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots (D19-1)

Copied to clipboard

Challenge: Existing studies focus on matching candidate responses with every context utterance, but it also brings noise signals and unnecessary information.
Approach: They propose a multi-hop selector network to match context with candidate responses . they propose to use a selector to filter the relevant utterances as context .
Outcome: The proposed model outperforms state-of-the-art methods on three public multi-turn dialogue datasets.
Few-Shot Named Entity Recognition: An Empirical Baseline Study (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods to build named entity recognition systems with limited labeled data are lacking.
Approach: They propose three orthogonal schemes to build named entity recognition systems when labeled data is limited.
Outcome: The proposed NER systems outperform existing methods on few-shot and training-free settings.
RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems (2021.acl-long)

Copied to clipboard

Challenge: Existing task-oriented dialog systems are less than satisfactory in robustness evaluation . existing systems are weak in robustity evaluation based on pre-training and fine-tuning .
Approach: They propose to use a set of training examples to evaluate model generalization ability . they propose to include tasks with limited training data to favor models with strong generalization abilities .
Outcome: The proposed model generalizes well with limited training data and is robust to user input across domains.
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies show that multi-head attention is an effective module in deep neural networks, but there are no explicit mechanisms guaranteeing this property.
Approach: They propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model’s expressiveness.
Outcome: The proposed approach improves the repulsiveness in multi-head attention and strengthens model’s expressiveness.
Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks (2024.naacl-long)

Copied to clipboard

Challenge: Existing vision-language models focus on salient attributes but ignore contextualized nuances, resulting in gender bias.
Approach: They propose a task-agnostic generation framework to mitigate gender bias in vision-language models.
Outcome: The proposed framework can mitigate gender bias in vision-language models . it yields all-sided but gender-obfuscated narratives, which prevents concentration on localized image features, especially gender attributes.
Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for language understanding and understanding can be trained to provide contextualized representations of words based on text data.
Approach: They propose a large-scale language VAE model Optimus that is pre-trained on large text corpus and fine-tuned for various language generation and understanding tasks.
Outcome: The proposed model achieves new state-of-the-art on VAE language modeling benchmarks.
Joint Embedding of Words and Labels for Text Classification (P18-1)

Copied to clipboard

Challenge: Existing approaches to text classification use word embeddings to capture semantic regularities between words.
Approach: They propose to view text classification as a label-word joint embedding problem . they use a framework that measures compatibility between text sequences and labels .
Outcome: The proposed framework outperforms the state-of-the-art methods on large text datasets.
Few-shot Natural Language Generation for Task-Oriented Dialog (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for NLG depend on heavily annotated data, which is infeasible for new domains.
Approach: They propose a system that converts a dialog act into a response in natural language . they propose 'nuclear language generation' to simulate a few-shot learning setting .
Outcome: The proposed model outperforms existing methods on a large set of annotated datasets.
LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models (2025.findings-naacl)

Copied to clipboard

Challenge: Current large foundational models have demonstrated transformative capabilities, approaching or surpassing human-level performances in many tasks.
Approach: They propose a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations.
Outcome: The proposed framework has 50 tasks and more than 10 models to promote transparent and reproducible evaluations.
Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have demonstrated that direct preference optimization (DPO) can be effective in generalizing large language models, but its effectiveness in video domain remains limited.
Approach: They propose a framework that utilizes detailed video captions as a proxy of video content to enable language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions.
Outcome: The proposed framework shows that it can be used to align language models with video content and improves performance on open-ended video QA tasks.
Implicit Deep Latent Variable Models for Text Generation (D19-1)

Copied to clipboard

Challenge: Variational auto-encoders have been used for text generation but their representation power is limited due to two reasons.
Approach: They advocate sample-based representations of variational distributions for natural language . they further develop an LVM to directly match the aggregated posterior to the prior .
Outcome: The proposed model can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue.
Scaling Vision-Language Models with Sparse Mixture of Experts (2023.findings-emnlp)

Copied to clipboard

Challenge: a study explores the effectiveness of mixture-of-experts (MoE) techniques in scaling vision-language models . alayrac and colleagues demonstrate the effectiveness and performance of MoE in scaling VLMs .
Approach: They propose to use sparsely-gated mixture-of-experts techniques to scale vision-language models . they show that MoE can achieve state-of the-art performance over dense models a range of benchmarks .
Outcome: The proposed approach achieves state-of-the-art performance over dense models of equivalent computational cost.
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training (2020.emnlp-main)

Copied to clipboard

Challenge: Existing pre-trained language models cannot be directly employed to generate text under specified lexical constraints.
Approach: They propose a method for insertion-based text generation that inserts tokens between existing tokens in a parallel manner.
Outcome: The proposed method is intuitive and interpretable on Wikipedia and Yelp datasets.
Unveiling the Spectrum of Data Contamination in Language Model: A Survey from Detection to Remediation (2024.findings-acl)

Copied to clipboard

Challenge: Data contamination is a problem in Large language models due to the reliance on extensive internet-derived training corpora.
Approach: They present a survey on the topic of data contamination in large language models.
Outcome: The results of the first survey on data contamination in large language models provide a comprehensive guide for NLP researchers seeking a systematic understanding of the issue.
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (P18-1)

Copied to clipboard

Challenge: Existing deep learning architectures to model compositionality in text sequences require a large number of parameters and expensive computations.
Approach: They propose two additional pooling strategies over word embeddings for improved interpretability and hierarchical pooling for spatial (n-gram) information within text sequences.
Outcome: The proposed pooling strategies improve interpretability and preserve spatial (n-gram) information within text sequences.
Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach: They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome: The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.
Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching (2021.tacl-1)

Copied to clipboard

Challenge: Existing methods for building task-oriented dialog systems are limited to a few tasks and domains.
Approach: They propose a method that uses transfer learning and machine teaching to build task bots at scale.
Outcome: The proposed method outperforms existing methods on well-studied task-oriented dialog benchmarks on well studied tasks.
Improving Text Generation with Student-Forcing Optimal Transport (2020.emnlp-main)

Copied to clipboard

Challenge: Maximum likelihood estimation (MLE) is used to train models, but during testing, the model is conditioned on previously generated tokens, resulting in exposure bias.
Approach: They propose to use optimal transport to match the sequences generated in MLE and test modes to reduce exposure bias.
Outcome: The proposed method is validated on machine translation, text summarization, and text generation tasks.
Robust Navigation with Language Pretraining and Stochastic Sampling (D19-1)

Copied to clipboard

Challenge: Existing methods to learn visual representations and action decoding schemes are limited to previously unseen instructions and environments.
Approach: They propose a stochastic sampling scheme to reduce the gap between the expert actions in training and sampled actions in test to correct its own mistakes.
Outcome: The proposed methods achieve 6% absolute gain over the previous best results on the Room-to-Room benchmark.
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing (N19-1)

Copied to clipboard

Challenge: Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing tasks.
Approach: They propose a cyclical annealing schedule which repeats the process of increasing multiple times to learn more meaningful latent codes progressively by leveraging previous learning cycles as warm re-restart.
Outcome: The proposed method improves on a broad range of NLP tasks, including language modeling, dialog response generation and semi-supervised text classification.
Better Late Than Never: Model-Agnostic Hallucination Post-Processing Framework Towards Clinical Text Summarization (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for generating concise and coherent summaries may include unintended text with hallucinations, causing computational costs.
Approach: They propose a model-agnostic framework to post-process medical hallucinations . MEDAL integrates with any medical summarization model, requiring no additional computational overhead .
Outcome: MEDAL can post-process medical hallucinations without additional computational overhead.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations