Papers by Yiming Yang

On the Sentence Embeddings from Pre-trained Language Models (2020.emnlp-main)

Challenge:	Existing approaches have limited successes in personalizing large language models due to the lack of personalized learning or the reliance on shared personal data.
Approach:	They propose a few-shot personalization of large language models with mis-aligned responses using LLMs by learning a set of personalized prompts for each user based on user profile and examples of previous opinions.
Outcome:	The proposed method significantly improves performance across benchmarks compared to best-performing baselines.

Copied to clipboard

Bohan Li, Hao Zhou, Junxian He, Mingxuan Wang, Yiming Yang, Lei Li

Improve Vision Language Model Chain-of-thought Reasoning (2025.acl-long)

Challenge:	Pre-trained contextual representations like BERT have been widely used for NLP tasks.
Approach:	They propose to transform anisotropic sentence embedding distribution to smooth and isotropic Gaussian distribution by normalizing flows that are learned with an unsupervised objective.
Outcome:	The proposed method achieves significant performance gains over state-of-the-art embeddings on a variety of semantic textual similarity tasks.

Copied to clipboard

Ruohong Zhang, Bowen Zhang, Yanghao Li, Haotian Zhang, Zhiqing Sun, Zhe Gan, Yinfei Yang, Ruoming Pang, Yiming Yang

Neural Language Modeling for Contextualized Temporal Graph Generation (2021.naacl-main)

Challenge:	Current training recipes often rely on datasets dominated by short annotations with limited rationales, hindering the models' ability to generalize to tasks requiring comprehensive reasoning.
Approach:	They propose a two-stage post-training strategy that augments short answers with CoT reasoning generated by GPT-4o, enhancing the VLM's CoT capabilities through fine-tuning.
Outcome:	The proposed strategy enhances the model's CoT capabilities through fine-tuning and reinforcement learning.

Copied to clipboard

Aman Madaan, Yiming Yang

Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedback (2022.findings-naacl)

Challenge:	Existing methods for temporal reasoning have been used for a number of applications, but their potential for tempor reasoning over event graphs has not been explored.
Approach:	They propose to use large-scale pre-trained language models to generate an event-level temporal graph from a document using existing IE/NLP tools.
Outcome:	The proposed method outperforms the closest existing method on several metrics on a hand-labeled, out-of-domain corpus.

Copied to clipboard

Niket Tandon, Aman Madaan, Peter Clark, Yiming Yang

A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text (D19-1)

Challenge:	Our approach pairs an LM with a growing memory of cases where the user identified an output error and provided general feedback on how to correct it.
Approach:	They propose to use an existing script generator to train a model to repair output errors without retraining.
Outcome:	The proposed model learns to apply user feedback to repair output errors while avoiding similar past mistakes on new, unseen examples.

Copied to clipboard

Bohan Li, Junxian He, Graham Neubig, Taylor Berg-Kirkpatrick, Yiming Yang

Representation Learning

Challenge:	Variational Autoencoders are powerful language models and effective representation learning frameworks.
Approach:	They propose a fix for posterior collapse which improves held-out likelihood, reconstruction and latent representation learning .
Outcome:	The proposed fix significantly improves held-out likelihood, reconstruction, and latent representation learning compared with previous state-of-the-art methods.

Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs (2023.emnlp-main)

Copied to clipboard

Pranjal Aggarwal, Aman Madaan, Yiming Yang, null Mausam

TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models (2022.acl-demo)

Challenge:	Existing methods for improving the correctness of output from large language models generate a constant number of samples per question, but Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%.
Approach:	They propose a model-agnostic technique that dynamically adjusts the number of samples per question using a lightweight stopping criterion.
Outcome:	The proposed technique reduces sample budget by 7.9 times with an average accuracy drop of less than 0.1%.

Copied to clipboard

Ziqing Yang, Yiming Cui, Zhigang Chen

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models (2024.findings-acl)

Challenge:	Large pre-trained language models have been used for many NLP tasks but computational resources are limited.
Approach:	They propose an open-source model pruning toolkit for pre-trained language models . they propose a self-supervised pruning method that can be applied without labeled data.
Outcome:	The proposed pruning method reduces model size without retraining the model and speeds up inference speed on the common CPU and GPU devices.

Copied to clipboard

Yiming Wang, Zhuosheng Zhang, Pei Zhang, Baosong Yang, Rui Wang

pEBR: A Probabilistic Approach to Embedding Based Retrieval (2025.emnlp-industry)

Challenge:	Existing methods rely on syntactically mapping natural languages to complete formal languages like Python and SQL.
Approach:	They propose to deconstruct reasoning-independent semantic information into generic symbolic representations, thereby efficiently capturing more generalized reasoning knowledge.
Outcome:	The proposed method improves in-context reasoning accuracy, learning efficiency, out-of-domain generalization, and output stability compared to the Chain-of thought technique.

Copied to clipboard

Han Zhang, Yunjiang Jiang, Mingming Li, Haowei Yuan, Yiming Qiu, Wen-Yun Yang

IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning (2023.findings-acl)

Challenge:	Existing embedding-based retrieval systems rely on heuristic and suboptimal cutoffs for item retrieval.
Approach:	They propose a probabilistic Embedding-Based Retrieval framework that learns a shared semantic representation space for both queries and items.
Outcome:	The proposed framework improves retrieval precision and recall, and ablation studies show it captures the differences between head-to-tail queries.

Copied to clipboard

Zihang Xu, Ziqing Yang, Yiming Cui, Shijin Wang

Learning to Correct for QA Reasoning with Black-box LLMs (2024.emnlp-main)

Challenge:	Existing systems for logical reasoning have surpassed the average performance of humans in many tasks like SQuAD but there is still a long way to go when it comes to logical reasoning.
Approach:	They propose an InDicator-Oriented Logic Pre-training task which logically strengthens pre-trained models with the help of 6 types of logical indicators and a logicalally rich dataset.
Outcome:	The proposed task achieves state-of-the-art on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC.

Copied to clipboard

Jaehyung Kim, Dongyoung Kim, Yiming Yang

Adversarial Training for Machine Reading Comprehension with Virtual Embeddings (2021.starsem-1)

Challenge:	Existing approaches to improve reasoning capability of large language models rely on accessibility or require significantly increased train- and inference-time costs.
Approach:	They propose a method to improve QA reasoning of large language models in a black-box setting by using a trained adaptation model to perform a seq2seq mapping from the often-imperfect reasonings of the original LLM to the correct or improved reasonings.
Outcome:	The proposed approach significantly improves reasoning accuracy across various QA benchmarks compared to the best-performing adaptation baselines.

Copied to clipboard

Ziqing Yang, Yiming Cui, Chenglei Si, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

CSLM: A Framework for Question Answering Dataset Generation through Collaborative Small Language Models (2024.findings-emnlp)

Challenge:	Neural networks are vulnerable to adversarial examples that have been mixed with certain perturbations.
Approach:	They propose a novel adversarial training method that perturbs the embedding matrix instead of word vectors to differentiate the roles of passages and questions.
Outcome:	The proposed method is effective universally and further improves the performance of MRC tasks.

Copied to clipboard

Yiming Wang, Yang Liu, Lingchen Wang, An Xiao

Agentic-R1: Distilled Dual-Strategy Reasoning (2025.emnlp-main)

Challenge:	Collecting high-quality question-answer (QA) pairs is vital for training large language models, but computational demands and associated costs often render such approaches prohibitive for the average researcher.
Approach:	They propose a small-scaled, open-source solution that generates QA pairs from documents or raw corpora using large-scale models like Llama-70B.
Outcome:	Experiments on domain-specific datasets show that the proposed model can generate high-quality QA pairs, making it accessible to a broader range of researchers.

Copied to clipboard

Weihua Du, Pranjal Aggarwal, Sean Welleck, Yiming Yang

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Challenge:	Current long chain-of-thought models rely on slow and error-prone natural language traces.
Approach:	They propose a framework that distills complementary reasoning strategies from multiple teachers into a unified student model.
Outcome:	The proposed framework improves accuracy on computation-intensive tasks and reduces inference latency on standard benchmarks.

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization (2025.acl-long)

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

Copied to clipboard

Nayu Liu, Junnan Zhu, Yiming Ma, Zhicong Lu, Wenlei Xu, Yong Yang, Jiang Zhong, Kaiwen Wei

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Existing decoding strategies neglect the explicit use of salient contextual information and rely on static hyperparameters to fix the balance between contextual and prior knowledge.
Approach:	They propose a salience-aware reinforced adaptive decoding (SARA) which incorporates salient contextual information and allows the model to determine reliance on source document's context, salient context, and model's prior knowledge based on pointwise mutual information.
Outcome:	The proposed model improves the quality and faithfulness of summaries across LLMs without modifying their weights.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Multimodal Invariant Sentiment Representation Learning (2025.findings-acl)

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

CINO: A Chinese Minority Pre-trained Language Model (2022.coling-1)

Challenge:	Existing methods for multimodal sensing ignore significant sentiment distribution imbalances and cross-modal sentiment conflicts, hindering performance improvement.
Approach:	They propose a method to learn stable multimodal invariant sentiment representations by incorporating distributional discrepancies and sentiment conflicts into the model training.
Outcome:	The proposed method improves MSA performance and achieves new state-of-the-art.

Copied to clipboard

Ziqing Yang, Zihang Xu, Yiming Cui, Baoxin Wang, Min Lin, Dayong Wu, Zhigang Chen

Multilinguality

Challenge:	Existing multilingual pre-trained language models do not perform well on some low-resource languages.
Approach:	They propose a multilingual pre-trained language model for Chinese minority languages . they collect documents from Wikipedia and construct two classification datasets .
Outcome:	The proposed model outperforms baseline models on various classification tasks.

PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification (2023.acl-long)

Copied to clipboard

Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang

Could you give me a hint ? Generating inference graphs for defeasible reasoning (2021.findings-acl)

Challenge:	Existing text classification frameworks require large amounts of human-labeled documents to train .
Approach:	They propose a contrastive learning framework that improves zero-shot text classification . they add prompts to enhance label retrieval and use retrieved labels to enrich training .
Outcome:	The proposed framework achieves state-of-the-art on four benchmark text classification datasets.

Copied to clipboard

Aman Madaan, Dheeraj Rajagopal, Niket Tandon, Yiming Yang, Eduard Hovy

A Re-evaluation of Knowledge Graph Completion Methods (2020.acl-main)

Challenge:	Defeasible reasoning is a mode of reasoning where conclusions can be overturned by taking into account new evidence.
Approach:	They propose to automatically generate inference graphs for a defeasible inference task by transfer learning from a related NLP task.
Outcome:	The proposed method generates meaningful graphs for a defeasible inference task and human accuracy improves by 20%.

Copied to clipboard

Zhiqing Sun, Shikhar Vashishth, Soumya Sanyal, Partha Talukdar, Yiming Yang

Structured Data in NLP

Challenge:	Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs.
Approach:	They propose a protocol to evaluate KGC methods that is robust to handle bias in the model, which can substantially affect the final results.
Outcome:	The proposed evaluation protocol is robust to handle bias in the model, which can substantially affect the final results.

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (2020.coling-main)

Copied to clipboard

Yiming Cui, Ting Liu, Ziqing Yang, Zhipeng Chen, Wentao Ma, Wanxiang Che, Shijin Wang, Guoping Hu

MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices (2020.acl-main)

Challenge:	Using cloze-style reading comprehension, Chinese machine reading comprehension datasets are becoming more and more popular . a new task is proposed to fill the right candidate sentence into the passage with several blanks .
Approach:	They propose a Chinese task to fill the right candidate sentence into a passage with blanks . they build a dataset to evaluate the difficulty of the task and make fake candidates .
Outcome:	The proposed task fills the right candidate sentence into the passage with blanks . the proposed dataset contains over 100K blanks within over 10K passages based on Chinese narrative stories .

Copied to clipboard

Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, Denny Zhou

TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing (2020.acl-demos)

Challenge:	Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE . BERT is one of the largest models ever in NLP, but suffers from heavy model size and high latency .
Approach:	They propose a tool to compress and accelerate the popular BERT model by task-agnostic application.
Outcome:	The proposed model is 4.3x smaller and 5.5x faster than BERT_BASE . it achieves competitive results on well-known benchmarks .

Copied to clipboard

Ziqing Yang, Yiming Cui, Zhipeng Chen, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

Conditional set generation using Seq2seq models (2022.emnlp-main)

Challenge:	Large pre-trained language models have hundreds of millions of parameters and take several gigabytes of memory to train and inference.
Approach:	They propose an open-source knowledge distillation toolkit designed for natural language processing that provides a set of predefined distillation methods and can be extended with custom code.
Outcome:	The proposed method is comparable with or even higher than the public distilled BERT models with similar numbers of parameters.

Copied to clipboard

Aman Madaan, Dheeraj Rajagopal, Niket Tandon, Yiming Yang, Antoine Bosselut

Low-resource Cross-lingual Event Type Detection via Distant Supervision with Minimal Effort (C18-1)

Challenge:	Several NLP tasks are instances of set generation.
Approach:	They propose a model-independent data augmentation approach that enlarges the model with the signals of order-invariance and cardinality.
Outcome:	The proposed method improves performance on four benchmark datasets with no additional annotations.

Copied to clipboard

Aldrian Obaja Muis, Naoki Otani, Nidhi Vyas, Ruochen Xu, Yiming Yang, Teruko Mitamura, Eduard Hovy

Multilinguality

Challenge:	Currently, few or no language processing tools or resources exist for most languages . a problem is that there is not enough available training data even in resource-rich languages if the task is complex.
Approach:	They propose to use a bilingual dictionary to train machine learning in a resource-poor language . they also explore adversarial training of bilingual word representations .
Outcome:	The proposed approach gives similar performance in event-type detection tasks.

Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement (2025.acl-long)

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Ziyang Huang, Yequan Wang, Siqi Fan, Yiming Ju, Jun Zhao, Kang Liu

Challenge:	Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states.
Approach:	They propose a method that enhances the utilization of contextual knowledge within LLMs’ internal representations by employing V-usable information analysis.
Outcome:	The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge.

CompleQA: Benchmarking the Impacts of Knowledge Graph Completion Methods on Question Answering (2023.findings-emnlp)

Copied to clipboard

Donghan Yu, Yu Gu, Chenyan Xiong, Yiming Yang

Dynamic Transformers Provide a False Sense of Efficiency (2023.acl-long)

Challenge:	Existing studies have focused on Knowledge Graph Completion as an end in itself, neglecting its potential impact on subsequent applications.
Approach:	They propose a benchmark to assess the impact of representative KGC methods on Knowledge Graph Question Answering (KGQA) they use a knowledge graph with 3 million triplets across 5 distinct domains to evaluate their results.
Outcome:	The proposed benchmark compares four well-known methods with two state-of-the-art systems to assess the impact of incomplete knowledge graphs on KGQA.

Copied to clipboard

Yiming Chen, Simin Chen, Zexin Li, Wei Yang, Cong Liu, Robby Tan, Haizhou Li

Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM (2024.eacl-long)

Challenge:	Pre-trained language models typically lead to high computational cost during inference.
Approach:	They propose a slowdown attack framework that can reduce inference efficiency by 80% by leveraging existing adversarial attacks targeting model accuracy.
Outcome:	The proposed framework can reduce the efficiency of multi-exit models by 80% on average, validating its effectiveness and generalization ability.

Copied to clipboard

Ruohong Zhang, Yau-Shian Wang, Yiming Yang

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	a novel method to train a smaller model with LLMs for zero-shot text classification requires immense computational resources due to their substantial model size.
Approach:	They propose a method which leverages the generative power of large language models to train a smaller model.
Outcome:	The proposed method outperforms state-of-the-art methods when limited data is available.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

Memory-assisted prompt editing to improve GPT-3 after deployment (2022.emnlp-main)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Aman Madaan, Niket Tandon, Peter Clark, Yiming Yang

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Challenge:	Large LMs such as GPT-3 can commit mistakes that are obvious to humans, such as interpreting “What word is similar to good?” to mean a homophone, while the user intended a synonym.
Approach:	They pair GPT-3 with a growing memory of cases where the model misunderstood the user’s intents, along with user feedback for clarification.
Outcome:	The proposed model can correct misunderstandings on four lexical tasks and two advanced ethical reasoning tasks without retraining.

Copied to clipboard

Ruohong Zhang, Liangke Gui, Zhiqing Sun, Yihao Feng, Keyang Xu, Yuanhan Zhang, Di Fu, Chunyuan Li, Alexander G Hauptmann, Yonatan Bisk, Yiming Yang

CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution (2026.acl-long)

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.

Copied to clipboard

Shidong Yang, Ziyu Ma, Tongwen Huang, Yiming Hu, Yong Wang, Xiangxiang Chu

Challenge:	Extensive experiments on AppWorld and BFCL demonstrate consistent and significant improvements over strong base models, yielding absolute gains of 19.43%, 15.58%, and 18.14%, respectively.
Approach:	They propose a framework that extracts feedback signals such as forgetting and uncertainty from rollout trajectories and utilizes them to guide LLM-based task synthesis.
Outcome:	Extensive experiments on AppWorld and BFCL show that the proposed framework improves over strong base models.

Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data (2025.acl-long)

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Robustness in NLP

Challenge:	Existing studies focus on optimizing model structures to handle uncertain missingness, but models still face challenges when dealing with uncertain missing data.
Approach:	They propose a data-centric robust multimodal sentiment analysis method, Proxy-Driven Robust Multimodal Fusion, which maps unimodal data to the latent space of Gaussian distributions to capture core features and structure.
Outcome:	The proposed method outperforms existing models in noise resistance and achieves state-of-the-art performance on multiple benchmark datasets.

Think about it! Improving defeasible reasoning by first modeling the question scenario. (2021.emnlp-main)

Copied to clipboard

Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Peter Clark, Yiming Yang, Eduard Hovy

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Existing literature suggests that a person forms a mental model of the problem scenario before answering questions.
Approach:	They propose to have a model first create a graph of relevant influences and leverage that graph as an additional input when answering a defeasible query.
Outcome:	The proposed model achieves state-of-the-art on three different defeasible reasoning datasets.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions (2023.findings-eacl)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Ruohong Zhang, Yau-Shian Wang, Yiming Yang, Donghan Yu, Tom Vu, Likun Lei

Information Retrieval

Challenge:	Extreme Multi-label text classification (XMTC) is a tough challenge due to the sheer size of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions.
Approach:	They propose to use a trained bag-of-words classifier to generate pseudo label descriptions from a training bag- of-word classifier.
Outcome:	The proposed approach outperforms the existing models in the tail label prediction problem and achieves state-of-the-art (SOTA) performance on XMTC benchmark datasets.

SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning (2024.acl-long)

Copied to clipboard

Guoxin Chen, Kexin Tang, Chao Yang, Fuying Ye, Yu Qiao, Yiming Qian

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese (2025.emnlp-main)

Challenge:	Existing methods focus on single-step reasoning, ignoring logical dependencies between steps.
Approach:	They propose a method that maximizes a structure-based return to facilitate structured reasoning and explanation.
Outcome:	The proposed method outperforms state-of-the-art methods on EntailmentBank and STREET benchmarks.

Copied to clipboard

Yikang Liu, Wanyang Zhang, Yiming Wang, Jialong Tang, Pei Zhang, Baosong Yang, Fei Huang, Rui Wang, Hai Hu

Machine Translation

Challenge:	Translationese is a linguistic property that is often introduced in the translation process that is different from those of original texts.
Approach:	They propose to use synthesized translations and translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments.
Outcome:	The proposed measure can generalize to unseen genres, authors, and language pairs.

Transformer-XL: Attentive Language Models beyond a Fixed-Length Context (P19-1)

Copied to clipboard

Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc Le, Ruslan Salakhutdinov

Fast Adaptation via Prompted Data: An Efficient Cross-Domain Fine-tuning Method for Large Language Models (2024.lrec-main)

Challenge:	Term memory networks (RNNs) are difficult to optimize due to gradient vanishing and explosion.
Approach:	They propose a neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence.
Outcome:	The proposed method improves state-of-the-art performance on short and long sequences and generates coherent, novel text articles with thousands of tokens.

Copied to clipboard

Yiming Zhang, Hantao Yang, Haobo Wang, Jake Zhao

DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis (2025.findings-acl)

Challenge:	Large language models (LLMs) have been successful in a variety of natural language understanding tasks, but domain discrepancies between the downstream task and the pre-training corpora may have hindered LLMs to excel further in the vertical applications.
Approach:	They propose a Fast Adaptation method for LLMs via Prompted Data that integrates downstream text corpora, gold labels and external knowledge sources into a highly controllable prompt.
Outcome:	The proposed method bridges the gap between the downstream task and the pre-training corpora and integrates downstream text corpors, gold labels and external knowledge sources into a highly controllable prompt.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Sentiment Analysis

Challenge:	Existing methods assume a direct alignment between images and aspects, matching the entire image with a corresponding aspect. Existing algorithms assume 'direct alignment' between images, introducing noise.
Approach:	They propose a Dual-Aware Enhanced Alignment Network (DaNet) that can enhance fine-grained multimodal aspect-image alignment and denoising.
Outcome:	The proposed system outperforms existing methods in three subtasks and is available on https://github.com/***/DaNet.

SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Copied to clipboard

Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin

Benchmarking Robustness of Machine Reading Comprehension Models (2021.findings-acl)

Challenge:	Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach:	They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome:	The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.

Copied to clipboard

Chenglei Si, Ziqing Yang, Yiming Cui, Wentao Ma, Ting Liu, Shijin Wang

Robustness in NLP

Challenge:	Existing benchmarks only evaluate models' robustness under test-time perturbations or adversarial attacks.
Approach:	They propose a model-agnostic benchmark to evaluate models' robustness under adversarial attacks.
Outcome:	The proposed model-agnostic benchmark evaluates models under four different types of adversarial attacks.

Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Copied to clipboard

Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning (2026.findings-acl)

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.

Copied to clipboard

Kun Wang, Li Yiming, Mingcheng Qu, Aqiang Zhang, Guang Yang, Tonghua Su

Politeness Transfer: A Tag and Generate Approach (2020.acl-main)

Challenge:	Existing methods for procedural planning over-rely on visual inputs and lack structured semantic information.
Approach:	They propose a vision–language framework for multimodal procedural planning that exploits implicit spatial relations and deep semantics encoded in object attributes.
Outcome:	The proposed framework outperforms existing methods in terms of execution success rate, LCS, and planning correctness.

Copied to clipboard

Aman Madaan, Amrith Setlur, Tanmay Parekh, Barnabas Poczos, Graham Neubig, Yiming Yang, Ruslan Salakhutdinov, Alan W Black, Shrimai Prabhumoye

Challenge:	Prior work on text style transfer has not focused on politeness as a style transfer task and we argue that defining it is cumbersome.
Approach:	They propose a task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning.
Outcome:	The proposed model outperforms state-of-the-art methods on content preservation and style transfer accuracy.

Language Models of Code are Few-Shot Commonsense Learners (2022.emnlp-main)

Copied to clipboard

Aman Madaan, Shuyan Zhou, Uri Alon, Yiming Yang, Graham Neubig

Unsupervised Cross-lingual Transfer of Word Embedding Spaces (D18-1)

Challenge:	Existing approaches to generate graphs using pre-trained language models hinder their ability to generate them correctly.
Approach:	They propose to frame structured commonsense reasoning tasks as code generation tasks instead of serializing the output graph as a flat list of nodes and edges.
Outcome:	The proposed approach outperforms natural-language LMs in three natural language tasks even when the downstream task does not involve source code at all.

Copied to clipboard

Ruochen Xu, Yiming Yang, Naoki Otani, Yuexin Wu

Multilinguality

Challenge:	Existing methods for cross-lingual word mapping require cross-linguistic supervision, but this is not available for many low resource languages.
Approach:	They propose an unsupervised method that learns transformation functions over corresponding word embedding spaces using a distributed distributional matching algorithm.
Outcome:	The proposed method performs better on bilingual lexicon induction and cross-lingual word similarity prediction datasets than other supervised and unsupervised methods.

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference (2024.findings-emnlp)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Yang Han, Yiming Wang, Rui Wang, Lu Chen, Kai Yu

Information Extraction & Text Mining

Challenge:	Text summarization tasks employ Pre-trained Language Models (PLMs) to fit diverse datasets.
Approach:	They propose a human summarization preference alignment framework to align PLMs with human preferences.
Outcome:	The proposed framework narrows the gap between automatic and human evaluations by integrating three components.

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering (2022.acl-long)

Copied to clipboard

Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng

Logic Traps in Evaluating Attribution Scores (2022.acl-long)

Challenge:	Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module.
Approach:	They propose a new open-domain question-answering framework that uses a knowledge-enhanced version of FiD to improve the approach.
Outcome:	The proposed model improves on ODQA benchmark datasets with less than 40% computation cost.

Copied to clipboard

Yiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang, Kang Liu, Jun Zhao

Automated Tone Transcription and Clustering with Tone2Vec (2024.findings-emnlp)

Challenge:	Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict.
Approach:	They propose to review existing methods for evaluating attribution scores and summarize the logic traps in these methods.
Outcome:	The proposed methods show that they do not contain logic traps and that they are not reliable.

Copied to clipboard

Yi Yang, Yiming Wang, ZhiQiang Tang, Jiahong Yuan

Text Clustering

Challenge:	Lexical tones play a crucial role in Sino-Tibetan languages, but current phonetic fieldwork relies on manual effort.
Approach:	They propose a pitch-based similarity representations for tone transcription called Tone2Vec . they propose an open-source package that facilitates automated fieldwork and analysis .
Outcome:	Experiments on dialect clustering and variance show that Tone2Vec captures fine-grained tone variation.

Transformer-based Speech Model Learns Well as Infants and Encodes Abstractions through Exemplars in the Poverty of the Stimulus Environment (2025.coling-main)

Copied to clipboard

Yi Yang, Yiming Wang, Jiahong Yuan

Active Retrieval Augmented Generation (2023.emnlp-main)

Challenge:	Existing theories of language learning for infants are inadequate, according to Chomsky . infants learn language in impoverished environments, according a new study .
Approach:	They designed a series of tasks, scenarios, and metrics to simulate the POS . they found that the emerging speech model wav2vec2.0 can learn well in noisy Mandarin environments.
Outcome:	The proposed model can learn in noisy and sparse Mandarin environments.

Copied to clipboard

Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig