Papers by Ge Gao
DisCo_Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec (2026.acl-long)
Copied to clipboard
Tao Li, Wenshuo Ge, Zhichao Wang, Zihao Cui, Yong Ma, Yingying Gao, Chao Deng, Shilei Zhang, Junlan Feng
| Challenge: | DisCo-Speech is a zero-shot controllable text-to-speech framework . standard codecs entangle timbre and prosody, which hinders independent control in continuation-based LMs. |
| Approach: | They propose a disentangled speech codec and an LM-based generator to solve this problem . they propose fusion and reconstruction that merges content and prosody into unified tokens . |
| Outcome: | DisCo-Speech achieves competitive voice cloning and superior zero-shot prosody control. |
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law (2025.acl-long)
Copied to clipboard
Qiming Ge, Shuhao Xing, Songyang Gao, Yunhua Zhou, Yicheng Zou, Songyang Zhang, Zhi Chen, Hang Yan, Qi Zhang, Qipeng Guo, Kai Chen
| Challenge: | Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands. |
| Approach: | They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability. |
| Outcome: | The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities. |
BU-NEmo: an Affective Dataset of Gun Violence News (2022.lrec-1)
Copied to clipboard
Carley Reardon, Sejin Paik, Ge Gao, Meet Parekh, Yanling Zhao, Lei Guo, Margrit Betke, Derry Tanti Wijaya
| Challenge: | Using a dataset that contains headline and image pairings from 840 news articles, we explore the relationship between image and text influence on human emotional response. |
| Approach: | They propose to use a U.S. gun violence news dataset that contains headline and image pairings from 840 news articles with 15K high-quality crowdsourced annotations on emotional responses. |
| Outcome: | The proposed dataset includes annotations on the dominant emotion experienced with the content, the intensity of the selected emotion and an open-ended, written component. |
Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translations (2025.emnlp-main)
Copied to clipboard
Yimin Xiao, Yongle Zhang, Dayeon Ki, Calvin Bao, Marianna J. Martindale, Charlotte Vaughn, Ge Gao, Marine Carpuat
| Challenge: | Using machine translation tools for everyday tasks is becoming more commonplace, but a lack of evaluation strategies and alternatives can cause users to over-rely on it. |
| Approach: | They propose to use MT evaluation techniques to promote MT quality and MT literacy among its users. |
| Outcome: | The findings highlight the need for evaluation and NLP explanation techniques to promote MT quality and MT literacy among its users. |
Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses (2026.acl-long)
Copied to clipboard
Chongyuan Dai, Yaling Shen, Zihan Gao, Jia Li, Yishun Jiang, Yaxiong Wang, Liu Liu, Zongyuan Ge, Jinpeng Hu
| Challenge: | Culture is a fundamental determinant of human affective processing and affective perceptions are often limited by declarative knowledge or established societal customs. |
| Approach: | They propose a multimodal benchmark that leverages LLM-generated provisional labels to isolate cross-cultural emotional distinctions. |
| Outcome: | The proposed benchmark captures cross-cultural emotional distinctions and derives reliable ground-truth annotations through human evaluation. |
I Could’ve Asked That: Reformulating Unanswerable Questions (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing large language models do not assist users in reformulating unanswerable questions . a recent study found that the models failed to reformulate questions based on assumptions that conflict with or cannot be verified with the information available in documents. |
| Approach: | They evaluate open-source and proprietary LLMs on couldAsk to evaluate their performance . they found that GPT-4 and Llama2-7B successfully reformulate questions only 26% and 12% of the time . |
| Outcome: | The proposed model successfully reformulates questions only 26% and 12% of the time . the proposed model is not able to reformulate questions, but it can be improved . |
Simulating Bandit Learning from User Feedback for Extractive Question Answering (2022.acl-long)
Copied to clipboard
| Challenge: | Explicit feedback from users can be used to continually improve system performance. |
| Approach: | They study the potential of learning from user feedback for extractive question answering by simulating feedback using supervised data. |
| Outcome: | The proposed model improves on a few examples and can be deployed in new domains without any data annotation effort. |
CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models (2025.findings-naacl)
Copied to clipboard
Shangda Wu, Yashan Wang, Ruibin Yuan, Guo Zhancheng, Xu Tan, Ge Zhang, Monan Zhou, Jing Chen, Xuefeng Mu, Yuejie Gao, Yuanliang Dong, Jiafeng Liu, Xiaobing Li, Feng Yu, Maosong Sun
| Challenge: | Current music information retrieval systems struggle to meet linguistic diversity challenges . current systems struggle with text queries in non-English languages . |
| Approach: | They propose a music information retrieval system that supports both ABC notation and MIDI . CLaMP 2 includes a multilingual text encoder and a multiple-modal music encoder . |
| Outcome: | The proposed system achieves state-of-the-art results in multilingual semantic search and music classification across modalities. |
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experiments show that models trained on multi-way parallel data outperform those trained on unaligned data. |
| Approach: | They propose a large-scale, high-quality multi-way parallel corpus based on TED Talks that spans 113 languages with up to 50 languages aligned in parallel. |
| Outcome: | The proposed model outperforms models trained on unaligned multilingual data on six multilingual benchmarks. |
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design (2026.findings-acl)
Copied to clipboard
Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu, Yicheng Zou, Qipeng Guo
| Challenge: | Existing approaches to RLVR use multiple-choice questions as verifiable rewards . however, not all tasks provide reliable verification . |
| Approach: | They propose a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning. |
| Outcome: | The proposed method significantly improves reasoning capabilities of Large Language Models. |
Continually Improving Extractive QA via Human Feedback (2023.emnlp-main)
Copied to clipboard
| Challenge: | a study of extractive question answering systems using human feedback shows promising potential for continual learning. |
| Approach: | They study extractive question answering system by using user feedback to improve it . they design and deploy an iterative approach where users ask questions and provide feedback . |
| Outcome: | The proposed model improves over time across different data regimes and domains . human user feedback is more affordable and abundant than annotations provided by trained experts . |
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning (2024.findings-naacl)
Copied to clipboard
Tianhua Zhang, Jiaxin Ge, Hongyin Luo, Yung-Sung Chuang, Mingye Gao, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, James Glass
| Challenge: | Existing methods for surfacing symbolic reasoning capabilities are limited to narrow tasks . arithmetic computations are unnatural to perform in pure language space, and hence present difficulties for LLMs. |
| Approach: | They propose a natural language embedded program framework for solving symbolic reasoning tasks. |
| Outcome: | The proposed framework improves on strong baselines across math and symbolic reasoning, text classification, question answering, and instruction following tasks. |
Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation (2024.lrec-main)
Copied to clipboard
Ge Gao, Jongin Kim, Sejin Paik, Ekaterina Novozhilova, Yi Liu, Sarah T. Bonna, Margrit Betke, Derry Tanti Wijaya
| Challenge: | Existing methods for classifying discrete emotions from news headlines have been limited to using headlines. |
| Approach: | They propose to use people’s free-text explanations to classify emotions elicited by news headlines to generate emotion explanations from headlines. |
| Outcome: | The proposed method improves on methods that only use headlines and train a pretrained model for explanation generation. |
MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)
Copied to clipboard
Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang
| Challenge: | Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences. |
| Approach: | They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge. |
| Outcome: | The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria. |
Dialogue Medical Information Extraction with Medical-Item Graph and Dialogue-Status Enriched Representation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches ignore relationships between medical items and statuses in the multi-turn doctor-patient dialogue. |
| Approach: | They propose a task to extract structured medical information from free text dialogues . they propose 'Dialogue Medical Information Extraction' to model relationships between items . |
| Outcome: | The proposed model outperforms previous models and achieves state-of-the-art performance on the public benchmark data set. |
Physician Detection of Clinical Harm in Machine Translation: Quality Estimation Aids in Reliance and Backtranslation Identifies Critical Errors (2023.emnlp-main)
Copied to clipboard
| Challenge: | a major challenge in the practical use of Machine Translation (MT) is that users lack information on translation quality to make informed decisions about how to rely on outputs. |
| Approach: | They evaluate quality estimation feedback in vivo with a human study in a medical setting. |
| Outcome: | The proposed method improves appropriate reliance on MT, but backtranslation helps detect harmful errors. |
CapOnImage: Context-driven Dense-Captioning on Image (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing image captioning systems generate narrative captions for images, which are spatially detached from the image in presentation. |
| Approach: | They propose a task called captioning on image which generatesense captions at different locations of the image based on contextual information. |
| Outcome: | The proposed model achieves the best results in both captioning accuracy and diversity aspects. |
LLM-SLM Collaborative Framework of Idiomatic Expression Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for idiomatic expression generation lack parallel data and manual annotations. |
| Approach: | They propose an iterative LLM-SLM collaborative framework that replaces human supervision for idiomatic expression data generation. |
| Outcome: | The proposed framework outperforms DeepSeek-R1 in Chinese Idiom Polishing with a 25.2% improvement in accuracy. |
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability. |
| Approach: | They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses. |
| Outcome: | The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences. |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)
Copied to clipboard
Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang
| Challenge: | Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence. |
| Approach: | They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included . |
| Outcome: | The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model. |
Prediction of People’s Emotional Response towards Multi-modal News (2022.aacl-main)
Copied to clipboard
Ge Gao, Sejin Paik, Carley Reardon, Yanling Zhao, Lei Guo, Prakash Ishwar, Margrit Betke, Derry Tanti Wijaya
| Challenge: | BU-NEmo dataset extends from 320 to 1,297 news headline and lead image pairings and collects 38,910 annotations in a crowdsourcing experiment. |
| Approach: | They extend the U.S. gun violence news-to-emotions dataset from 320 to 1,297 news headline and lead image pairings and collect annotations in a crowdsourcing experiment. |
| Outcome: | The proposed models outperform baseline models on the NEmo+ dataset by large margins across several metrics. |
Neural Metaphor Detection in Context (D18-1)
Copied to clipboard
| Challenge: | Existing models focus on limited forms of linguistic context, such as unigrams. |
| Approach: | They propose end-to-end neural models for detecting metaphorical word use in context . they show that bi-directional biLSTM models which operate on complete sentences work well . |
| Outcome: | The proposed models show that they can learn rich contextual word representations . they are compared to previous models which focused on limited linguistic context . |
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)
Copied to clipboard
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou
| Challenge: | a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say . |
| Approach: | They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible . |
| Outcome: | The proposed framework achieves state-of-the-art performance among open-source projects. |
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design (2026.findings-acl)
Copied to clipboard
Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yu Guang Wang
| Challenge: | Recent deep generative models have already shown encouraging * Equal contribution. |
| Approach: | They propose to use generic instruction-tuned LLMs as direct text-to-sequence generators to achieve this goal. |
| Outcome: | Recent studies show that reflection improves sequence quality and alignment while maintaining competitive foldability. |
An Interdisciplinary Approach to Human-Centered Machine Translation (2025.emnlp-main)
Copied to clipboard
Marine Carpuat, Omri Asscher, Kalika Bali, Luisa Bentivogli, Fred Blain, Lynne Bowker, Monojit Choudhury, Hal Daumé Iii, Kevin Duh, Ge Gao, Alvin C Grissom II, Marzena Karpinska, Elaine C Khoong, William D. Lewis, Andre Martins, Mary Nurminen, Douglas W. Oard, Maja Popovic, Michel Simard, François Yvon
| Challenge: | Despite progress in MT, a gap persists between how the technology is developed and how it is used in real-world contexts. |
| Approach: | They propose a human-centered approach to machine translation (MT) they argue that MT should be evaluated with diverse goals and contexts of use . |
| Outcome: | The proposed approach emphasizes alignment of evaluation and design with diverse communicative goals and contexts of use. |
Navigating the OverKill in Large Language Models (2024.acl-long)
Copied to clipboard
Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
| Challenge: | Recent studies have highlighted a tendency among large language models to refuse to answer benign queries. |
| Approach: | They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding. |
| Outcome: | The proposed approach reduces the refusal rate by 20% while having little impact on safety. |