Papers by Mingda Chen
Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Large Language Models (RALMs) do not consistently outperform the original retrieval-free Language Model (LM). |
| Approach: | They propose a trainable framework that can adaptively retrieve from different knowledge sources and effectively decrease unpredictable reader errors. |
| Outcome: | The proposed framework significantly improves performance over the RALM with a single retriever by significantly reducing inconsistent behaviors. |
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations (N19-1)
Copied to clipboard
| Challenge: | Empirically, the model with the best performing syntactic and semantic representations gives rise to the most disentangled representations. |
| Approach: | They propose a generative model that uses latent variables to learn a sentence that uses both latent and latent representations. |
| Outcome: | The proposed model achieves better disentanglement between semantic and syntactic representations by training with multiple losses, including losses that exploit aligned paraphrastic sentences and word-order information. |
Mining Knowledge for Natural Language Inference from Wikipedia Categories (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Accurate lexical entailment (LE) and natural language inference (NLI) tasks require expensive annotations. |
| Approach: | They propose to pretrain Wikipedia categories for lexical entailment and natural language inference by pretraining them on WikiNLI and transferring them to other knowledge bases. |
| Outcome: | The proposed model can improve strong baselines such as BERT and RoBERTa by pretraining on WikiNLI and transferring the models on downstream tasks. |
Improving Factuality with Explicit Working Memory (2025.acl-long)
Copied to clipboard
Mingda Chen, Yang Li, Karthik Padthe, Rulin Shao, Alicia Yi Sun, Luke Zettlemoyer, Gargi Ghosh, Wen-tau Yih
| Challenge: | Large language models can generate factually inaccurate content, a problem known as hallucination. |
| Approach: | They propose an approach that integrates a working memory that receives feedback from external resources. |
| Outcome: | The proposed method outperforms baselines on four fact-seeking datasets and increases the factuality metric by 2 to 6 points absolute. |
Smaller Text Classifiers with Discriminative Cluster Embeddings (N18-2)
Copied to clipboard
| Challenge: | Word embeddings dominate overall model sizes in neural methods for natural language processing, especially when large vocabularies and high dimensions are used. |
| Approach: | They propose a Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. |
| Outcome: | The proposed method minimizes the task loss while maximizing over the latent clustering while remaining parameter-efficient. |
Improving In-Context Few-Shot Learning via Self-Supervised Training (2022.naacl-main)
Copied to clipboard
Mingda Chen, Jingfei Du, Ramakanth Pasunuru, Todor Mihaylov, Srini Iyer, Veselin Stoyanov, Zornitsa Kozareva
| Challenge: | Existing approaches to improve in-context few-shot learning are pretraining and downstream fewshot evaluation. |
| Approach: | They propose to use self-supervision as an intermediate training stage between pretraining and downstream fewshot usage to train models to perform in-context few shot learning. |
| Outcome: | The proposed model outperforms baseline models on two benchmarks. |
Controllable Paraphrase Generation with a Syntactic Exemplar (P19-1)
Copied to clipboard
| Challenge: | Prior work on controllable text generation assumes that the generated attribute can take on a finite set of values known a priori. |
| Approach: | They propose a task where the syntax of a generated sentence is controlled rather by a sentential exemplar. |
| Outcome: | The proposed model achieves improvements over baselines and learns to capture desirable characteristics. |
WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for data-to-text generation focus on single-sentence generation or long-form generation. |
| Approach: | They create a dataset that pairs Wikipedia sections with tabular data and various metadata. |
| Outcome: | The proposed dataset can generate fluent and high quality texts but struggle with coherence and factuality. |
Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations (D19-1)
Copied to clipboard
| Challenge: | Prior work on pretrained sentence embeddings and benchmarks focused on the capabilities of stand-alone sentences. |
| Approach: | They propose a test suite of tasks to evaluate whether sentence representations include broader context information. |
| Outcome: | The proposed training objectives help to encode different aspects of information in document structures. |
Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering (2024.eacl-long)
Copied to clipboard
| Challenge: | Recent approaches to multi-hop question answering rely on in-context learning . however, these models contain billions of parameters making them inefficient at inference time. |
| Approach: | They propose a framework that allows for improving smaller language models with less than 10 human-annotated QA pairs by synthesizing millions of multi-hop questions and claims to fine tune language models. |
| Outcome: | The proposed framework improves model performance on multi-hop question answering and fact verification benchmarks while being almost one-third the size in parameter count. |
xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages (2023.acl-short)
Copied to clipboard
| Challenge: | xsim++ provides a reliable proxy for bitext mining without expensive pipelines. |
| Approach: | They propose a new proxy proxy based on similarity in a multilingual embedding space . they validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages and then train NMT systems on the mined data. |
| Outcome: | The proposed proxy improves on xsim++ and trains on the mined data. |
SummScreen: A Dataset for Abstractive Screenplay Summarization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing summarization datasets are constructed from various domains, such as news, and we characterize them using two entity-centric metrics. |
| Approach: | They propose to use a summarization dataset to evaluate TV series transcripts and recaps . they propose to employ two entity-centric metrics to evaluate the dataset . |
| Outcome: | The proposed model outperforms the existing model and its oracle counterparts in character overlap and accuracy. |
ImpRAG: Retrieval-Augmented Generation with Implicit Queries (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) systems treat retrieval and generation as separate processes, requiring explicit textual queries to connect them. |
| Approach: | They propose a query-free RAG system that integrates retrieval and generation into a unified model. |
| Outcome: | The proposed system can achieve 3.6-11.5 accuracy improvements on unseen tasks . it allows models to express their information needs without human-specified queries . |
Variational Sequential Labelers for Semi-Supervised Learning (D18-1)
Copied to clipboard
| Challenge: | a family of multitask variational methods for semi-supervised sequence labeling is currently unclear how to use them in the context of sequence labelling. |
| Approach: | They propose a family of multitask variational methods for semi-supervised sequence labeling using latent variables and a discriminative labeler. |
| Outcome: | The proposed models outperform standard sequential baselines on 8 sequence labeling datasets and improve further with unlabeled data. |
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)
Copied to clipboard
Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin
| Challenge: | Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning. |
| Approach: | They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps. |
| Outcome: | The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets. |
BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric (2023.acl-long)
Copied to clipboard
Mingda Chen, Paul-Ambroise Duquenne, Pierre Andrews, Justine Kao, Alexandre Mourachko, Holger Schwenk, Marta R. Costa-jussà
| Challenge: | End-to-End speech-to speech translation is generally evaluated with text-based metrics . this means generated speech has to be automatically transcribed, making the evaluation dependent on ASR systems. |
| Approach: | They propose a text-free evaluation metric for end-to-end speech-tospeech translation, named BLASER, to avoid the dependency on automatic speech recognition systems. |
| Outcome: | The proposed metric avoids the dependency on automatic speech recognition systems by encoding generated speech segments into a shared embedding space. |
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)
Copied to clipboard
Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang
| Challenge: | Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows . |
| Approach: | They propose a repository-level evaluation benchmark to assess security of AI-generated code. |
| Outcome: | The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation. |
EntEval: A Holistic Evaluation Benchmark for Entity Representations (D19-1)
Copied to clipboard
| Challenge: | EntEval is a test suite of tasks that require nontrivial understanding of entities. |
| Approach: | They propose to encode the mention context or the Wikipedia hyperlink annotations to learn better entity representations. |
| Outcome: | The proposed model improves strong baselines on multiple EntEval tasks. |