Papers by Haodong Zhao
VANE: Guiding High-Value Exploration in RLVR via Outcome-Process Novelty Shaping (2026.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on large-scale mathematical reasoning and out-of-distribution tasks demonstrate the effectiveness and generalization of the proposed method. |
| Approach: | They propose a method that quantifies novelty across the outcome space and semantic process space by using reward or solution divergence. |
| Outcome: | Experiments on Qwen2.5-Math-7B demonstrate the proposed method is general and efficient. |
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition (2023.acl-long)
Copied to clipboard
| Challenge: | Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical discourse relations among arguments. |
| Approach: | They propose a prompt-based multi-level implicit discourse relation recognition framework that leverages parameter-efficient prompt tuning to drive inputted arguments to match the pre-trained space. |
| Outcome: | The proposed framework achieves comparable results on PDTB 2.0 and 3.0 using about 0.1% trainable parameters compared with baselines. |
Turning Failures into Value: Negative Experience Replay for RLVR via Confidence Gating and Boundary Failure Sampling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing experience replay methods for RLVR ignore sample inefficiency . expensive reasoning trajectories are discarded immediately after a single gradient update . |
| Approach: | They propose a method to replay failure trajectories to improve model refinement . they propose 'nexGRPO' which employs mid-confidence gating to filter invalid noise and saturated errors. |
| Outcome: | The proposed model outperforms strong baaselines and achieves improved out-of-distribution generalization. |
UOR: Universal Backdoor Attacks on Pre-trained Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to attack pre-trained language models rely on manual selection of triggers and backdoor representations. |
| Approach: | They propose a backdoor attack method that turns manual selection into automatic optimization . they propose to use poisoned contrastive learning to learn more uniform backdoor representations . |
| Outcome: | The proposed method achieves better attack performance on text classification tasks compared to manual methods. |
Dual Capsule Attention Mask Network with Mutual Learning for Visual Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) models extract features from images and questions independently, but these methods fail to capture fine-grained key features and include much unnecessary information. |
| Approach: | They propose a dual capsule attention mask network with mutual learning for visual question answering (VQA) it contains two branches processing coarse-grained features and fine-grain features, respectively. |
| Outcome: | The proposed model outperforms baselines in terms of performance and interpretability and achieves new SOTA performance on the VQA-v2 dataset. |
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)
Copied to clipboard
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu
| Challenge: | Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity. |
| Approach: | They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards. |
| Outcome: | Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% . |
Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings . attribution under visual confounding is a central challenge in measuring social bias . |
| Approach: | They propose a face-only counterfactual evaluation paradigm that isolates demographic effects while preserving real-image realism. |
| Outcome: | The proposed paradigm isolates demographic effects while preserving real-image realism. |
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning (2025.findings-emnlp)
Copied to clipboard
Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai
| Challenge: | Large reasoning models (LRMs) incur excessive computational overhead due to redundant reasoning, especially on simple tasks. |
| Approach: | They propose an Adaptive Self-Recovery Reasoning framework that suppresses unnecessary reasoning and enables implicit recovery. |
| Outcome: | The proposed framework suppresses unnecessary reasoning and enables implicit recovery. |
Rejection-to-Acceptance Transition: Model Editing-Based Jailbreak Backdoor Injection Not Limited to Few Output Tokens (2026.findings-acl)
Copied to clipboard
Shiji Yang, Min Cai, Hao Xiong, Congyao Mei, Haodong Zou, Shicheng Tan, Jie Chen, Fulan Qian, Shu Zhao
| Challenge: | Existing methods for jailbreaking LLMs are implemented by binding backdoors to predefined phrases as first few output tokens, inducing the LLM’s next-token prediction to produce continuous responses. |
| Approach: | They propose a model editing-based jailbreak backdoor attack that hijacks LLM representations into a acceptance domain rather than binding to a few output tokens. |
| Outcome: | The proposed model editing method outperforms existing methods, showing stronger jailbreak capabilities across LLMs and datasets. |
Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous Prompts (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on the interpretability and transferability of continuous prompts have not been conducted on the subject. |
| Approach: | They propose to interpret continuous prompts as the weighting of discrete prompts by jointly optimizing prompt fidelity and downstream fidelity. |
| Outcome: | The proposed interpretations provide effective readability and plausibility, which is helpful to understand the decision-making of continuous prompts and discover potential shortcuts. |
Redundancy Principles for MLLMs Benchmarks (2025.acl-long)
Copied to clipboard
Zicheng Zhang, Xiangyu Zhao, Xinyu Fang, Chunyi Li, Xiaohong Liu, Xiongkuo Min, Haodong Duan, Kai Chen, Guangtao Zhai
| Challenge: | Rapid growth of Multi-modality Large Language Models has led to significant redundancy among benchmarks. |
| Approach: | They propose a framework to improve MLLM benchmark design by identifying redundancy at three levels: dimension, instance, and cross-benchmark redundancies. |
| Outcome: | The proposed framework streamlines evaluations and enhances reliability. |
Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA (2026.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge base question answering methods are limited by syntactic constraints and are prone to structural deviations that render queries unexecutable. |
| Approach: | They propose a framework that reframes semantic parsing as an iterative reasoning process driven by execution feedback. |
| Outcome: | The proposed method achieves significant improvements in query executability and answer accuracy on the WebQSP and CWQ datasets. |
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)
Copied to clipboard
Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao
| Challenge: | Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios. |
| Approach: | They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions. |
| Outcome: | The proposed framework improves generalization and realism of large language models under complex and irregular table conditions. |
Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for large language models adopt query-driven iterative reasoning from a local perspective, limiting efficiency and accuracy for complex multi-hop tasks. |
| Approach: | They propose a multi-view instructed adaptive reasoning of LLM on Knowledge Graphs that allows LLMs to plan, evaluate, and adapt reasoning paths from a global perspective. |
| Outcome: | The proposed model overcomes the limitations of local exploration by enabling LLMs to plan, evaluate, and adapt reasoning paths from a global perspective. |
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)
Copied to clipboard
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen
| Challenge: | Existing open-source multi-modal large language models (MLLMs) focus on enhancing foundational capabilities, leaving a significant gap in human preference alignment. |
| Approach: | They propose a dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs’ alignment with human preferences. |
| Outcome: | The proposed dataset of 200K high-quality training samples improves human preference alignment while maintaining or enhancing performance on standard VQA benchmarks. |