Papers by James Wang
Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations (2023.acl-long)
Copied to clipboard
| Challenge: | Human-annotated labels and explanations are critical for training explainable NLP models. |
| Approach: | They propose a metric that measures the usefulness of an explanation for model performance at both fine-tuning and inference. |
| Outcome: | The proposed metric can evaluate the quality of human-annotated explanations, while Simulatability falls short. |
FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking (2024.findings-emnlp)
Copied to clipboard
Zhuoer Wang, Leonardo Ribeiro, Alexandros Papangelis, Rohan Mukherjee, Tzu-Yen Wang, Xinyan Zhao, Arijit Biswas, James Caverlee, Angeliki Metallinou
| Challenge: | Existing supervised and in-context learning approaches suffer from high training costs, poor data efficiency, and generated API calls that can be unfaithful to the API documentation and the user’s request. |
| Approach: | They propose an output-side optimization approach that uses state-tracked constrained decoding and a lightweight model as the discriminator to rerank the beam-searched candidate generations of the large language model. |
| Outcome: | The proposed approach outperforms existing supervised and in-context learning approaches in the DSTC8 and API Bank datasets in terms of call generation accuracy, inference efficiency, and context efficiency. |
A Survey on LLMs for Story Generation (2025.findings-emnlp)
Copied to clipboard
Maria Teleki, Vedangi Bengali, Xiangjue Dong, Sai Tejas Janjur, Haoran Liu, Tian Liu, Cong Wang, Ting Liu, Yin Zhang, Frank Shipman, James Caverlee
| Challenge: | Methods for story generation with Large Language Models (LLMs) have come into the spotlight recently. |
| Approach: | They propose a novel taxonomy of LLMs for story generation consisting of two major paradigms: independent story generation by an LLM, and author-assistance for story creation . |
| Outcome: | The proposed taxonomy compares existing work on the topic with those of novel author-assistance models. |
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion (2024.emnlp-main)
Copied to clipboard
Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia Hu
| Challenge: | Existing mechanisms compromise ownership rights or raise data privacy concerns . existing mechanisms compromise security of released large language models . |
| Approach: | They propose a TaylorMLP to preserve the ownership of large language models by transforming the weights of LLMs into Taylor-series parameters instead of releasing original weights . |
| Outcome: | The proposed model preserves ownership of large language models and prevents their abuse by adjusting the generation speed and causing low-speed token generation. |
Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings (D19-1)
Copied to clipboard
| Challenge: | Current unsupervised adversarial methods for mapping monolingual word embeddings require high quality parallel data, such as a dictionary or sentence-aligned corpus. |
| Approach: | They propose a weakly-supervised adversarial training method which improves performance of previous unsupervised adversaries for most languages. |
| Outcome: | The proposed method improves the performance of previous unsupervised adversarial methods for most languages and especially for typologically distant language pairs. |
Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)
Copied to clipboard
Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister
| Challenge: | Large language models struggle to capture relevant information located in the middle of their input. |
| Approach: | They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle. |
| Outcome: | The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation performance. |
Can language models learn from explanations in context? (2022.findings-emnlp)
Copied to clipboard
Andrew Lampinen, Ishita Dasgupta, Stephanie Chan, Kory Mathewson, Mh Tessler, Antonia Creswell, James McClelland, Jane Wang, Felix Hill
| Challenge: | Language Models can adapt to a few in-context examples, but without training. |
| Approach: | They examine how explanations of few-shot examples can help Language Models (LMs) explanations can improve performance even without tuning, they find . |
| Outcome: | The proposed explanations outperform hand-tuned explanations on small validation sets. |
Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models are safety-aligned to prevent harmful response generation . prior work on jailbreak effectiveness has focused on analyzing success rate of jailbreaks . |
| Approach: | They propose to frame jailbreaks as inference-time alignment and draw suboptimal bounds . they also propose a Safety-Net to measure how vulnerable an LLM is to jailbreak attacks . |
| Outcome: | a new framework allows researchers to show how vulnerable an LLM is to jailbreaks . a Safety-Net measures how vulnerable the model is to attacks, the authors say . |
Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture (2023.findings-emnlp)
Copied to clipboard
Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis, Sayan Ghosh, Lihong He, Yuxuan Lu, Shashank Srivastava, Yunyao Li, James Hendler, Dakuo Wang
| Challenge: | Existing low-resource learning techniques focus on label annotation while neglecting the natural language explanation of a data point. |
| Approach: | They propose a novel architecture that leverages an explanation-generation model to produce explanations guided by human explanations and a prediction model that utilizes generated explanations toward prediction faithfully. |
| Outcome: | The proposed architecture produces explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a data diversity-based AL sampling strategy that benefits from the explanation annotations. |
Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)
Copied to clipboard
Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie
| Challenge: | Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores. |
| Approach: | They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs. |
| Outcome: | The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values. |
M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)
Copied to clipboard
Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu
| Challenge: | Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains. |
| Approach: | They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs. |
| Outcome: | The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods. |
Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasing (2024.acl-short)
Copied to clipboard
| Challenge: | Existing methods for Cross-Document Event Coreference Resolution (CDEC) are biased towards lexical similarities, limiting a crucial avenue of research in event comprehension. |
| Approach: | They propose a lexically rich variant of Event Coref Bank Plus (ECB+) for CDEC on symbolic and metaphoric language. |
| Outcome: | The proposed method avoids the reannotation of expensive coreference links on symbolic and metaphoric language. |
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)
Copied to clipboard
Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Ranran Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed ELsayed, Martha Palmer, Clare Voss, Cynthia Schneider, Boyan Onyshkevych
| Challenge: | a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications . |
| Approach: | a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19. |
| Outcome: | a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing . |
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge (2020.emnlp-main)
Copied to clipboard
| Challenge: | Paraphrase identification requires specialized domain knowledge to perform . state-of-the-art neural models and non-expert human annotators have poor performance on PARADE . |
| Approach: | They propose a benchmark dataset called PARADE for paraphrase identification that requires specialized domain knowledge. |
| Outcome: | The proposed dataset shows state-of-the-art models and non-expert human annotators have poor performance on PARADE. |
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)
Copied to clipboard
Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, Dragomir Radev
| Challenge: | Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models. |
| Approach: | They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries . |
| Outcome: | The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting. |
Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for candidate answer extraction are reliant on linguistic rules or annotated data and face partial annotation issue and challenges in generalization. |
| Approach: | They propose an unsupervised approach that leverages the inherent structure of context passages through a Differentiable Masker-Reconstructor (DMR) Model with the enforcement of self-consistency for picking up salient information tokens. |
| Outcome: | The proposed model outperforms supervised and unsupervised methods in two datasets with exhaustively-annotated answers and shows that it is comparable to supervised methods. |
Scaling Unverifiable Rewards: A Case Study on Visual Insights (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to scale complex, open-ended tasks with unverifiable rewards are not scalable to multi-stage pipelines. |
| Approach: | They propose a process-based refinement framework that scales inference across stages of a multi-agent pipeline, instead of refining a single output over time. |
| Outcome: | The proposed framework scales inference across stages of a multi-agent pipeline, instead of refining a single output over time as in prior work. |
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling (2024.findings-naacl)
Copied to clipboard
Bingsheng Yao, Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, Shao Zhang, Yisi Sang, Sijia Liu, James Hendler, Dakuo Wang
| Challenge: | Existing studies on LLM prompting focus on selecting a better set of data samples inside one single prompt input, but why not design and leverage multiple ICL prompts together to further improve the LLM’s performance? |
| Approach: | They propose a low-resource LLM prompting technique to optimize the construction of multiple ICL prompt inputs to produce confident predictions. |
| Outcome: | The proposed technique can produce confident predictions by optimizing the construction of multiple ICL prompt inputs on four NLI datasets and one QA dataset. |
Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)
Copied to clipboard
Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang
| Challenge: | Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models. |
| Approach: | This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy . |
| Outcome: | The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications. |
Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In task-oriented semantic parsing, the system aims to translate users’ utterances in natural language to machine-interpretable programs (API calls) However, Large Language Models (LLMs) are known to hallucinate and therefore pose a formidable challenge in constraining generated content. |
| Approach: | They propose to use large language models to translate user's utterances to machine-interpretable programs (API calls) they identify constraints violations in task-oriented utterrances and define fine-grained metrics that complement traditional ones. |
| Outcome: | The proposed methods reduce constraints violations and improve quality of the generated API calls, but require careful consideration given their implementation complexity and latency. |
On the Blind Spots of Model-Based Evaluation Metrics for Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text generation evaluation metrics are lacking in robustness analysis. |
| Approach: | They propose to use stress tests to test for errors in text generation evaluation metrics . they find that BERTScore is confused by truncation errors in summarization . |
| Outcome: | The proposed stress tests show that they are insensitive to errors in open-ended generation, translation, and summarization. |
DA3: A Distribution-Aware Adversarial Attack against Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent attacks have shown that adversarial examples have a different data distribution than the original examples, reducing their effectiveness under detection methods. |
| Approach: | They propose a distribution-aware adversarial attack method that considers the distribution shifts of adversarials to improve attacks’ effectiveness under detection methods. |
| Outcome: | The proposed method improves the effectiveness of adversarial examples under detection methods and integrates both ASR and detectability. |
Multi-Adversarial Learning for Cross-Lingual Word Embeddings (2021.naacl-main)
Copied to clipboard
| Challenge: | Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings without supervision, but their performance for distant languages is still not satisfactory. |
| Approach: | They propose a multi-adversarial method that induces the seed cross-lingual dictionary through multiple mappings, each induced to fit the mapping for one subspace. |
| Outcome: | The proposed method improves performance on bilingual lexicon induction and cross-lingual document classification on unsupervised bilingual linguistic induction. |
RAFT: Realistic Attacks to Fool Text Detectors (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have exhibited remarkable fluency across tasks, but their unethical applications are unclear. |
| Approach: | They propose a grammar error-free black-box attack that exploits LLM embeddings at the word-level while preserving original text quality. |
| Outcome: | The proposed attack compromises all detectors across domains and is transferable across source models. |
Development of Community-Oriented Text-to-Speech Models for Māori ‘Avaiki Nui (Cook Islands Māori) (2024.lrec-main)
Copied to clipboard
Jesin James, Rolando Coto-Solano, Sally Akevai Nicholas, Joshua Zhu, Bovey Yu, Fuki Babasaki, Jenny Tyler Wang, Nicholas Derby
| Challenge: | Text-to-speech synthesis is used to transform text into a synthesized voice for a specific language. |
| Approach: | They describe the development of a text-to-speech system for Mori ‘Avaiki Nui (Cook Islands Mi) they used two approaches to train the system, the HMM-system MaryTTS and the deep learning system FastSpeech2 . |
| Outcome: | The proposed system is based on the HMM-system MaryTTS and the deep learning system FastSpeech2 . the ground truth voice had the highest quality, but the fastspeech 2 voice had a significantly higher quality than the MaryTTs synthesized recordings. |
TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability (2025.emnlp-demos)
Copied to clipboard
Mohammad Aflah Khan, Ameya Godbole, Johnny Wei, Ryan Yixiang Wang, James Flemings, Krishna P. Gummadi, Willie Neiswanger, Robin Jia
| Challenge: | Existing workflows for pretraining large language models are cumbersome, fragmented and inaccessible. |
| Approach: | They propose an open-source library for editing, inspection, and analysis of large language model datasets. |
| Outcome: | TokenSmith is an open-source library for editing, inspection, and analysis of large language model datasets. |
Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models can encode unfair social biases from large pre-training corpora and even amplify biase in downstream applications. |
| Approach: | They propose a *debias-while-prompt tuning* method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks. |
| Outcome: | The proposed method can mitigate biases on three extrinsic bias benchmarks and adapt to existing debiased language models. |
End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MM-RAG is a promising approach for enhancing the reliability and factuality of large vision-language models . current methods focus on component-level optimizations and necessitate extensive component-specific training datasets . |
| Approach: | They propose a new paradigm that backpropagates global rewards to each component . this backpropage transforms local losses into specific local losses . |
| Outcome: | The proposed paradigm achieves high training efficiency on knowledge-intensive multimodal benchmarks. |
Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)
Copied to clipboard
Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Chengjian Zheng, Yanzhang He, Tara Sainath, Pedro Moreno Mengibar
| Challenge: | Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference. |
| Approach: | They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. |
| Outcome: | The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains. |
Closed-book Question Generation via Contrastive Learning (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent studies on open-book QG have achieved promising progress, but generating natural questions under a more practical closed-book setting remains a challenge. |
| Approach: | They propose a QG model that stores more information in its parameters through contrastive learning and an answer reconstruction module. |
| Outcome: | The proposed model outperforms baselines in automatic evaluation and human evaluation on a public dataset and a new WikiCQA dataset. |
ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing logical reasoning evaluations of Large Language Models (LLMs) focus on single-turn and static environments, such as arithmetic problems. |
| Approach: | They propose a Recursively Thinking-Ahead agent that analyzes the opponents’ future moves/actions and assigns reward signals for these situations. |
| Outcome: | The proposed agent is based on two scenarios: Online Racing and Offline Probing. |
Benchmarking Failures in Tool-Augmented Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | FAIL-TaLMs contains 1,749 examples using 906 tools across 21 categories, including single- and multi-tool usage. |
| Approach: | They introduce a benchmark to examine the shortcomings of tool-augmented language models (TaLMs) that assume 'perfect' information access and tool availability. |
| Outcome: | The proposed benchmark systematically evaluates 1,749 examples using 906 tools across 21 categories, including single- and multi-tool usage. |
CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Persona-assigned Large Language Models can be useful for personalized, context-aware reasoning. |
| Approach: | They propose a framework that harmonizes demographic perturbations into a unified prediction by balancing agreement and divergence among counterfactual personas. |
| Outcome: | The proposed framework improves reasoning performance even when base personas are suboptimal. |
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages (2024.emnlp-main)
Copied to clipboard
Holy Lovenia, Rahmad Mahendra, Salsabil Akbar, Lester James Miranda, Jennifer Santoso, Elyanah Aco, Akhdan Fadhilah, Jonibek Mansurov, Joseph Marvin Imperial, Onno Kampman, Joel Moniz, Muhammad Habibi, Frederikus Hudi, Jann Montalan, Ryan Hadiwijaya, Joanito Lopo, William Nixon, Börje Karlsson, James Jaya, Ryandito Diandaru, Yuze Gao, Patrick Irawan, Bin Wang, Jan Christian Blaise Cruz, Chenxi Whitehouse, Ivan Parmonangan, Maria Khelli, Wenyu Zhang, Lucky Susanto, Reynard Ryanda, Sonny Hermawan, Dan Velasco, Muhammad Kautsar, Willy Hendria, Yasmin Moslem, Noah Flynn, Muhammad Adilazuarda, Haochen Li, Johanes Lee, R. Damanhuri, Shuo Sun, Muhammad Qorib, Amirbek Djanibekov, Wei Qi Leong, Quyet V. Do, Niklas Muennighoff, Tanrada Pansuwan, Ilham Firdausi Putra, Yan Xu, Tai Chia, Ayu Purwarianti, Sebastian Ruder, William Tjhi, Peerat Limkonchotiwat, Alham Aji, Sedrick Keh, Genta Winata, Ruochen Zhang, Fajri Koto, Zheng Xin Yong, Samuel Cahyawijaya
| Challenge: | Southeast Asia (SEA) is home to over 1,300 indigenous languages and 671 million people . prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA . |
| Approach: | They propose to provide a resource center that provides standardized corpora in nearly 1,000 SEA languages across three modalities. |
| Outcome: | a new benchmark assesses the quality of AI models on 36 SEA languages across 13 tasks . the results highlight the importance of SEA as a culturally diverse region . |
LAMP-MedQA: A Lightweight Multi-Agent System for Patient-Oriented Medical Question Answering (2026.acl-srw)
Copied to clipboard
| Challenge: | Large language models (LLMs) are a promising way to bridge the gap between patient health literacy and access to care. |
| Approach: | They evaluate a range of open- and closed-source LLMs on a MeDiSumQA dataset . they propose a lightweight multi-agent framework for patient-oriented medical question answering . |
| Outcome: | The proposed model achieves lower FKGL than zero-shot GPT-5 and highest simplification quality among all models. |