Ming Li


2024

pdf bib
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Ming Li | Yong Zhang | Zhitao Li | Jiuhai Chen | Lichang Chen | Ning Cheng | Jianzong Wang | Tianyi Zhou | Jing Xiao
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model’s expected responses and its intrinsic generation capability. Through the application of IFD, cherry samples can be pinpointed, leading to a marked uptick in model training efficiency. Empirical validations on datasets like Alpaca and WizardLM underpin our findings; with a mere 10% of original data input, our strategy showcases improved results. This synthesis of self-guided cherry-picking and the IFD metric signifies a transformative leap in the instruction tuning of LLMs, promising both efficiency and resource-conscious advancements. Codes, data, and models are available.

pdf bib
Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
Ming Li | Jiuhai Chen | Lichang Chen | Tianyi Zhou
Findings of the Association for Computational Linguistics ACL 2024

Making LLMs speak for different, especially minority groups of people, and generate statements supporting their diverse or even controversial perspectives is critical to creating an inclusive environment. However, existing LLMs lack sufficient controllability to the stance of their generated content, which often contains inconsistent, neutral, or biased statements. In this paper, we improve the controllability of LLMs in generating statements supporting an argument the user defined in the prompt. We find that multi-round debates between two LLMs with opposite stances generate higher-quality and more salient statements for each, which are important training data to improve the controllability of LLMs. Motivated by this, we develop a novel debate & tuning (“DEBATUNE”) pipeline finetuning LLMs to generate the statements obtained via debate. To examine DEBATUNE, we curate the largest dataset of debate topics so far, which covers 710 controversial topics and corresponding arguments for each topic. Evaluations by the GPT-4 judge with a novel controversy controllability metric show that LLMs’ capability of generating diverse perspectives is significantly improved by DEBATUNE. Moreover, such controllability can be generalized to unseen topics, generating high-quality statements supporting controversial arguments.

pdf bib
Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
Ming Li | Lichang Chen | Jiuhai Chen | Shwai He | Jiuxiang Gu | Tianyi Zhou
Findings of the Association for Computational Linguistics ACL 2024

Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving the data quality but often overlook the compatibility of the data with the student model being finetuned. This paper introduces Selective Reflection-Tuning, a novel paradigm that synergizes a teacher LLM’s reflection and introspection for improving existing data quality with the data selection capability of the student LLM, to automatically refine existing instruction-tuning data. This teacher-student collaboration produces high-quality and student-compatible instruction-response pairs, resulting in sample-efficient instruction tuning and LLMs of superior performance. Selective Reflection-Tuning is a data augmentation and synthesis that generally improves LLM finetuning and self-improvement without collecting brand-new data. We apply our method to Alpaca and WizardLM data and achieve much stronger and top-tier 7B and 13B LLMs.

pdf bib
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Ming Li | Yong Zhang | Shwai He | Zhitao Li | Hongyu Zhao | Jianzong Wang | Ning Cheng | Tianyi Zhou
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to perceive instruction difficulty and data selection results. This enables us to use a much smaller and more efficient model to filter the instruction data used to train a larger language model. Not only does it largely speed up the data filtering, but the filtered-data-finetuned LLM achieves even better performance on standard benchmarks. Extensive experiments validate the efficacy and efficiency of our approach.

2023

pdf bib
Semi-supervised News Discourse Profiling with Contrastive Learning
Ming Li | Ruihong Huang
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
Haoyan Yang | Zhitao Li | Yong Zhang | Jianzong Wang | Ning Cheng | Ming Li | Jing Xiao
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generators formulate the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their advanced QA capabilities, but they are typically too large to be fine-tuned with budget constraints while some of them are only accessible via APIs. To tackle this issue and further improve ReQA performance, we propose a trainable Pluggable Reward-Driven Contextual Adapter (PRCA), keeping the generator as a black box. Positioned between the retriever and generator in a Pluggable manner, PRCA refines the retrieved information by operating in a token-autoregressive strategy via maximizing rewards of the reinforcement learning phase. Our experiments validate PRCA’s effectiveness in enhancing ReQA performance on three datasets by up to 20% improvement to fit black-box LLMs into existing frameworks, demonstrating its considerable potential in the LLMs era.

2021

pdf bib
Don’t Change Me! User-Controllable Selective Paraphrase Generation
Mohan Zhang | Luchen Tan | Zihang Fu | Kun Xiong | Jimmy Lin | Ming Li | Zhengkai Tu
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

In the paraphrase generation task, source sentences often contain phrases that should not be altered. Which phrases, however, can be context dependent and can vary by application. Our solution to this challenge is to provide the user with explicit tags that can be placed around any arbitrary segment of text to mean “don’t change me!” when generating a paraphrase; the model learns to explicitly copy these phrases to the output. The contribution of this work is a novel data generation technique using distant supervision that allows us to start with a pretrained sequence-to-sequence model and fine-tune a paraphrase generator that exhibits this behavior, allowing user-controllable paraphrase generation. Additionally, we modify the loss during fine-tuning to explicitly encourage diversity in model output. Our technique is language agnostic, and we report experiments in English and Chinese.

pdf bib
Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering
Minghan Li | Ming Li | Kun Xiong | Jimmy Lin
Findings of the Association for Computational Linguistics: EMNLP 2021

Multi-task dense retrieval models can be used to retrieve documents from a common corpus (e.g., Wikipedia) for different open-domain question-answering (QA) tasks. However, Karpukhin et al. (2020) shows that jointly learning different QA tasks with one dense model is not always beneficial due to corpus inconsistency. For example, SQuAD only focuses on a small set of Wikipedia articles while datasets like NQ and Trivia cover more entries, and joint training on their union can cause performance degradation. To solve this problem, we propose to train individual dense passage retrievers (DPR) for different tasks and aggregate their predictions during test time, where we use uncertainty estimation as weights to indicate how probable a specific query belongs to each expert’s expertise. Our method reaches state-of-the-art performance on 5 benchmark QA datasets, with up to 10% improvement in top-100 accuracy compared to a joint-training multi-task DPR on SQuAD. We also show that our method handles corpus inconsistency better than the joint-training DPR on a mixed subset of different QA datasets. Code and data are available at https://github.com/alexlimh/DPR_MUF.

pdf bib
Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach
Anup Anand Deshmukh | Qianqiu Zhang | Ming Li | Jimmy Lin | Lili Mou
Findings of the Association for Computational Linguistics: EMNLP 2021

In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages. We propose a knowledge-transfer approach that heuristically induces chunk labels from state-of-the-art unsupervised parsing models; a hierarchical recurrent neural network (HRNN) learns from such induced chunk labels to smooth out the noise of the heuristics. Experiments show that our approach largely bridges the gap between supervised and unsupervised chunking.

pdf bib
Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2
He Bai | Peng Shi | Jimmy Lin | Luchen Tan | Kun Xiong | Wen Gao | Jie Liu | Ming Li
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

The semantics of a text is manifested not only by what is read but also by what is not read. In this article, we will study how those implicit “not read” information such as end-of-paragraph () and end-of-sequence () affect the quality of text generation. Specifically, we find that the pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage. Experimental results on English story generation show that can lead to higher BLEU scores and lower perplexity. We also conduct experiments on a self-collected Chinese essay dataset with Chinese-GPT2, a character level LM without and during pre-training. Experimental results show that the Chinese GPT2 can generate better essay endings with .

2020

pdf bib
Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data
Hamidreza Shahidi | Ming Li | Jimmy Lin
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.

2019

pdf bib
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features
Wei Yang | Luchen Tan | Chunwei Lu | Anqi Cui | Han Li | Xi Chen | Kun Xiong | Muzi Wang | Ming Li | Jian Pei | Jimmy Lin
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)

Consumers dissatisfied with the normal dispute resolution process provided by an e-commerce company’s customer service agents have the option of escalating their complaints by filing grievances with a government authority. This paper tackles the challenge of monitoring ongoing text chat dialogues to identify cases where the customer expresses such an intent, providing triage and prioritization for a separate pool of specialized agents specially trained to handle more complex situations. We describe a hybrid model that tackles this challenge by integrating recurrent neural networks with manually-engineered features. Experiments show that both components are complementary and contribute to overall recall, outperforming competitive baselines. A trial online deployment of our model demonstrates its business value in improving customer service.

pdf bib
End-to-End Open-Domain Question Answering with BERTserini
Wei Yang | Yuqing Xie | Aileen Lin | Xingyu Li | Luchen Tan | Kun Xiong | Ming Li | Jimmy Lin
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)

We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

pdf bib
End-to-End Neural Context Reconstruction in Chinese Dialogue
Wei Yang | Rui Qiao | Haocheng Qin | Amy Sun | Luchen Tan | Kun Xiong | Ming Li
Proceedings of the First Workshop on NLP for Conversational AI

We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context. Following a standard decomposition of the context reconstruction task into referring expression detection and coreference resolution, we propose a novel end-to-end architecture for separately and jointly accomplishing this task. Key features of this model include POS and position encoding using CNNs and a novel pronoun masking mechanism. One perennial problem in building such models is the paucity of training data, which we address by augmenting previously-proposed methods to generate a large amount of realistic training data. The combination of more data and better models yields accuracy higher than the state-of-the-art method in coreference resolution and end-to-end context reconstruction.

2016

pdf bib
Entity Disambiguation by Knowledge and Text Jointly Embedding
Wei Fang | Jianwen Zhang | Dilin Wang | Zheng Chen | Ming Li
Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning

2010

pdf bib
Measuring the Non-compositionality of Multiword Expressions
Fan Bu | Xiaoyan Zhu | Ming Li
Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)

2004

pdf bib
Discovering Patterns to Extract Protein-Protein Interactions from Full Biomedical Texts
Minlie Huang | Xiaoyan Zhu | Donald G. Payan | Kunbin Qu | Ming Li
Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA/BioNLP)