Papers by Bo Gao
Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Social media has become a fertile ground for nurturing rumors and misinformation due to its lack of systematic moderation. |
| Approach: | They propose a framework to enhance the joint predictive capabilities of LLMs for stance detection and rumor verification tasks. |
| Outcome: | The proposed framework outperforms state-of-the-art methods and generalizes to non-LLMs accommodated as task models. |
ICLER: Intent CLassification with Enhanced Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for intent classification are inadequate in identifying micro-grained intentions . ICLER is based on In-Context Learning, but it is inadequate in enterprise vertical domains . |
| Approach: | They propose an intent classification method with enhanced reasoning that optimizes the embedding model to capture subtle sentence-level information. |
| Outcome: | The proposed method outperforms existing methods in intent identification tasks in vertical domains. |
A Generative Pre-Trained Language Model for Channel Prediction in Wireless Communications Systems (2025.emnlp-main)
Copied to clipboard
Bo Lin, Huanming Zhang, Yuhua Jiang, Yucong Wang, Tengyu Zhang, Shaoqiang Yan, Hongyao Li, Yihong Liu, Feifei Gao
| Challenge: | Existing model-based channel prediction methods suffer from limited accuracy due to imperfect temporal modeling, while existing AI-based methods suffers from limited generalization due to inadequate training strategies. |
| Approach: | They propose a generative pre-trained language model for channel prediction based on channel correlation and train it based upon transformer decoder architecture. |
| Outcome: | The proposed model can learn various channel characteristics and perform impressive tasks across multiple dimensions. |
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework (2023.findings-acl)
Copied to clipboard
Yangyi Chen, Hongcheng Gao, Ganqu Cui, Lifan Yuan, Dehan Kong, Hanlu Wu, Ning Shi, Bo Yuan, Longtao Huang, Hui Xue, Zhiyuan Liu, Maosong Sun, Heng Ji
| Challenge: | Existing models of robustness evaluation are incomprehensive, impractical, and invalid . |
| Approach: | They propose a framework for automatic robustness evaluation that shifts towards model-centric evaluation to further exploit the advantages of adversarial attacks. |
| Outcome: | The proposed framework is based on a model-centric evaluation protocol and a robustness evaluation protocol. |
CodeExp: Explanatory Code Document Generation (2022.findings-emnlp)
Copied to clipboard
Haotian Cui, Chenglong Wang, Junjie Huang, Jeevana Priya Inala, Todd Mytkowicz, Bo Wang, Jianfeng Gao, Nan Duan
| Challenge: | Existing code-to-text generation models produce only high-level code summaries that do not capture implementation-level choices essential for these scenarios. |
| Approach: | They propose a code explanation generation task that uses code docstrings to refine models. |
| Outcome: | The proposed model can generate well-structured long docstrings comparable to human-written ones. |
Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience (2025.findings-acl)
Copied to clipboard
Jiawei Gu, Ziting Xian, Yuanzhen Xie, Ye Liu, Enjie Liu, Ruichao Zhong, Mochi Gao, Yunzhi Tan, Bo Hu, Zang Li
| Challenge: | Large language models struggle to infer implicit relationships embedded in tabular formats . authors introduce a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning (ICL). |
| Approach: | They propose a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning to simulate human-like knowledge transfer. |
| Outcome: | Experiments on Text-to-SQL and TableQA show CoRE significantly improves performance . it achieves gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks . |
DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (2026.acl-long)
Copied to clipboard
Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang
| Challenge: | Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored. |
| Approach: | They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator. |
| Outcome: | Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%. |
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su
| Challenge: | Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context. |
| Approach: | They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration. |
| Outcome: | Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness. |
Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing knowledge graph question answering methods only search for the answer in a large knowledge graph. |
| Approach: | They propose to partition retrieved knowledge subgraphs into smaller sub-KSGs and then use a graph-augmented learning to rank method to select the top-ranked sub-kSGs. |
| Outcome: | The proposed method can capture global interactions in question and subgraphs and local interactions on the full KSG and top-ranked sub-KSGs respectively. |
HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on posthoc alignment techniques, but the underlying safety mechanisms within LVLMs remain unexplored. |
| Approach: | They propose a tuning-free framework that leverages internal activations to enhance safety. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in detecting jailbreak attacks against large vision-language models. |
Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)
Copied to clipboard
Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo
| Challenge: | Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity. |
| Approach: | They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability. |
| Outcome: | The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability. |
Positive Text Reframing under Multi-strategy Optimization (2025.coling-main)
Copied to clipboard
| Challenge: | Existing positive reframing models can be fine-tuned to achieve acceptable results, but generating fluent, diverse text remains a challenge. |
| Approach: | They propose a positive reframing sentiment reward and content preservation reward framework . they propose re-ranking methods that optimize for style and consistency . |
| Outcome: | The proposed framework improves on unconstrained and controlled positive reframing tasks. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient (2025.acl-long)
Copied to clipboard
| Challenge: | Recent pruning methods rely on heuristically hand-crafted metrics, leading to suboptimal performance. |
| Approach: | They propose a method that optimizes pruning masks by minimizing back-propagation . they learn an underlying Bernoulli distribution to sample binary pruning mask samples . |
| Outcome: | The proposed method is able to support global and heterogeneous pruning without back-propagation. |
Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for few-shot text classification often encounter problems drawing accurate class prototypes from support set samples. |
| Approach: | They propose a meta-learning method that leverages the information within the task itself . they propose Query-Data-Augmenter and Label-Adapter to build a task-adaptive metric space . |
| Outcome: | The proposed method shows obvious advantages over state-of-the-art models on eight benchmark datasets. |
HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)
Copied to clipboard
Hao Zhang, Zhenjia Li, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, null Xiaoxincc, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers. |
| Approach: | They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters . |
| Outcome: | The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork. |
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)
Copied to clipboard
Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability . |
| Approach: | They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR . |
| Outcome: | The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks. |
IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)
Copied to clipboard
Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen
| Challenge: | Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content. |
| Approach: | They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question . |
| Outcome: | The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types. |
CEPT: A Contrast-Enhanced Prompt-Tuning Framework for Emotion Recognition in Conversation (2024.lrec-main)
Copied to clipboard
| Challenge: | Emotion recognition in conversation research suffers from data imbalance and the presence of similar linguistic expressions for different emotions. |
| Approach: | They propose a Contrast-Enhanced Prompt-Tuning framework that transforms an ERC task into a Masked Language Modeling task and generates the emotion for each utterance in the conversation. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on all three benchmark datasets and excels in recognizing minority emotions. |
FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)
Copied to clipboard
Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen
| Challenge: | Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. |
| Approach: | They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings. |
| Outcome: | The proposed framework achieves the strongest overall performance across all models. |
DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection (2025.naacl-industry)
Copied to clipboard
| Challenge: | Current intent detection work experiments with minor intent categories. |
| Approach: | They propose a retrieval-augmented generation framework that uses query-to-query and query- to-metadata approaches to retrieve intents from metadata. |
| Outcome: | The proposed framework improves on query-to-query (Q2Q) and query- to-metadata (Q 2M) approaches. |
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models. |
BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing work on illustrated storybooks decomposes this task into separate stages, limiting multi-modal grounding . et al. proposes a safety-aware multi-agent collaboration framework for high-quality, safety-conscious visual narratives . |
| Approach: | They propose a safety-aware multi-agent collaboration framework for illustrated storybooks . the framework jointly plans, scripts, illustrates, and globally corrects inconsistencies . |
| Outcome: | a novel framework outperforms existing methods in safety and coherence, and improves visual consistency . the framework is available on github at https://github.com/bogao-code/BookAgent/main . |
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)
Copied to clipboard
Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E
| Challenge: | AEGIS examines whether current models can effectively audit AI-generated images in academic papers. |
| Approach: | They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics. |
| Outcome: | AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis. |
SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)
Copied to clipboard
Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang
| Challenge: | Large language models (LLMs) have many advantages but they also pose significant safety risks. |
| Approach: | They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions . |
| Outcome: | The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets. |
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)
Copied to clipboard
Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu
| Challenge: | Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents . |
| Approach: | They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks. |
| Outcome: | The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents . |
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)
Copied to clipboard
Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao
| Challenge: | Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL). |
| Approach: | They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
| Outcome: | The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
CORN: Co-Reasoning Network for Commonsense Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work uses two independent modules to model QA content and external commonsense knowledge graph (KG) Existing research uses two separate modules to create QA contextual text representations and relationships between QA entities. |
| Approach: | They propose a commonsense question answering (QA) model that uses two independent modules to model QA contextual text representation and relationships between QA entities in KG. |
| Outcome: | The proposed model achieves state-of-the-art on QA benchmarks in the CommonsenseQA and OpenBookQA datasets. |
Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model (2025.findings-acl)
Copied to clipboard
Cong Gao, Bo Zhang, Linkang Yang, Minghao Hu, Zhunchen Luo, Xiaoying Bai, Guotong Geng, Jun Zhang, Yunhua Xue
| Challenge: | Existing red-teaming methods require expensive fine-tuning, especially for large LLMs. |
| Approach: | They propose a red-teaming method that uses an ‘evil score’ to evaluate the potential of tokens to contribute to harmful outputs during decoding. |
| Outcome: | The proposed method achieves an ASR of 92.83% on the Llama-3.2-3B-Instruct model, compared to 83.48% with adversarial fine-tuning while using less computational resources. |
Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness (2021.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that inappropriate language can cause models to output profanity . authors propose a training framework to prevent such outputs from hurting the usability of models . |
| Approach: | proposed training framework eliminates the causes that trigger the generation of profanity . authors propose a framework that leverages a short list of profans to prevent this . |
| Outcome: | a proposed training framework can prevent models from generating profanity . the proposed framework leverages a short list of profanities examples . |