Papers by Qiaozhu Mei
ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) struggle with ex-ante reasoning—making inferences or predictions without access to future information. |
| Approach: | They propose a benchmark that assesses LLMs’ ex-ante inference ability across four tasks: stock prediction, question answering, Wikipedia event generation, and scientific publication generation. |
| Outcome: | The proposed benchmark assesses LLMs’ ex-ante inference ability across four tasks. |
MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows (2025.findings-naacl)
Copied to clipboard
Xingjian Zhang, Yutong Xie, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, Qiaozhu Mei
| Challenge: | Scientific innovation is driven by detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, and planning new research. |
| Approach: | They propose to use large language models to extract five key aspects from scientific publications to optimize scientific workflows. |
| Outcome: | The proposed dataset includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. |
PRewrite: Prompt Rewriting with Reinforcement Learning (2024.acl-short)
Copied to clipboard
| Challenge: | Prompt engineering is done manually in a trial-and-error ad-hoc fashion, authors say . |
| Approach: | They propose a method to rewrite an under-optimized prompt to a more effective prompt. |
| Outcome: | The proposed method rewrites an under-optimized prompt to a more effective prompt. |
Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation methods for natural language generation are inadequate . distinguishing machine-generated text is challenging even for human evaluators . |
| Approach: | They compare human-based evaluators with automated evaluation procedures . they find human evaluers do not correlate well with discriminative evalators . |
| Outcome: | The proposed evaluation methods are compared with a dozen state-of-the-art generators for online product reviews. |
The Strength of the Weakest Supervision: Topic Classification Using Class Labels (N19-3)
Copied to clipboard
| Challenge: | a topic classifier can understand only class labels when training for tasks that require a large amount of labeled documents. |
| Approach: | They propose an algorithm that can initialize a topic classifier using only class labels . they propose a method that combines word embedding and naive Bayes classification . |
| Outcome: | The proposed approach saves significant initial labeling effort by providing a "warm start" the proposed approach can be fine-tuned with more labeled documents to reach a certain performance level. |
Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Recent LLMs like Gemini-1.5 and GPT-4 show exceptional capabilities to understand long contexts directly. |
| Approach: | They propose a method that routes queries to RAG or LC based on model self-reflection. |
| Outcome: | The proposed method significantly reduces the computation cost while maintaining a comparable performance to RAG. |
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts (D18-1)
Copied to clipboard
| Challenge: | Existing work on explaining classifier decisions has not addressed local feature redundancy . a common way to explain why a model classified an example is to extract a sparse subset of features that were responsible for the decision . |
| Approach: | They propose an adversarial method for producing high-recall explanations of text classifier decisions . they use a method which scans the residual of attention for remaining predictive signal . |
| Outcome: | The proposed method produces high-recall explanations of text classifier decisions . it uses a set of human-annotated personal attacks to evaluate the impact . |
Bridging the Preference Gap between Retrievers and LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on retrievers and LLMs treat them as separate components . a novel bridge model is proposed to optimize the relationship between the retriever and the LLM . |
| Approach: | They propose a framework that chains together supervised and reinforcement learning to train a bridge model that optimizes the connection between the retriever and the LLM. |
| Outcome: | Empirical results show that the proposed model optimizes the connection between the retriever and the LLM. |
Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification (2021.acl-long)
Copied to clipboard
| Challenge: | Text simplification reduces the language complexity of professional content for accessibility purposes. |
| Approach: | They propose that text simplification can be decomposed into a pipeline of tasks . they show that the pipeline can be used to predict whether a text needs to be simplified . |
| Outcome: | The proposed model improves the performance of out-of-sample simplification tests on a blackbox lexical model . the proposed model reduces the complexity of professional text by a large margin . |