Papers by Ziyi Liu
A Dual Contrastive Learning Framework for Enhanced Multimodal Conversational Emotion Recognition (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods struggle to capture emotion shifts due to label replication and fail to preserve positive independent modality contributions during fusion. |
| Approach: | They propose a Dual Contrastive Learning Framework that enhances existing MERC models without additional data. |
| Outcome: | The proposed framework outperforms existing models on two MERC benchmark datasets and shows that it reduces label dependence and enhances emotion-sensitive independent modality features. |
AdaFuse: Adaptive Ensemble Decoding for Large Language Models (2026.acl-long)
Copied to clipboard
Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He
| Challenge: | Existing ensemble approaches to large language models lack flexibility for mid-generation adaptation. |
| Approach: | They propose an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation. |
| Outcome: | The proposed framework outperforms existing ensemble frameworks on open-domain QA, arithmetic reasoning, and machine translation tasks. |
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales (2023.acl-long)
Copied to clipboard
Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, Xiang Ren
| Challenge: | Existing metrics like task performance of the LM generating the rationales or similarity between generated and gold rationale are not good indicators of their human utility. |
| Approach: | They propose to use a large language model to generate rationales with better human utility by estimating its conciseness and novelty. |
| Outcome: | The proposed model can measure human utility to a better extent by estimating its usefulness in answering similar unseen instances. |
LongVideoAgent: Multi-Agent Reasoning with Long Videos (2026.acl-long)
Copied to clipboard
| Challenge: | a key emerging challenge is robust long video understanding, authors say . current methods compress content into lossy summaries or rely on limited toolsets . |
| Approach: | They propose a multi-agent framework where a master LLM coordinates a grounding agent and a vision agent to extract targeted textual observations. |
| Outcome: | The proposed model outperforms strong non-agent baselines on episode-level datasets . the proposed model significantly outperformed existing models on other datasets. |
A Unified Supervised and Unsupervised Dialogue Topic Segmentation Framework Based on Utterance Pair Modeling (2025.naacl-long)
Copied to clipboard
| Challenge: | Unsupervised methods for dialogue topic segmentation are difficult to surpass due to short sentences, serious references and non-standard language. |
| Approach: | They propose a method to divide a dialogue into different topic paragraphs to better understand its structure and content. |
| Outcome: | The proposed method achieves the best results on multiple benchmark datasets across different scenarios. |
Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media (2025.acl-long)
Copied to clipboard
| Challenge: | Social media platforms are experiencing a growing presence of AI-Generated Texts (AIGTs) however, the misuse of AIGTs could have profound implications for public opinion . |
| Approach: | They collect a dataset with 2.4M posts from 3 major social media platforms . they then construct a diverse dataset to train and evaluate AIGT detectors . |
| Outcome: | The proposed dataset analyzes 2.4M posts from 3 major social media platforms from 2022 to 2024 . it finds that Medium and Quora show marked increases in AAR . |
Self-contradictory reasoning evaluation and detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive reasoning ability, but many downstream reasoning tasks focus on performance-wise evaluation. |
| Approach: | They define and assess the Self-Contra rate across three datasets and delve into finer-grained categories of Self-contra reasoning. |
| Outcome: | The proposed model can detect self-contra reasoning with a 52.2% F1 score, much lower than for humans. |
InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated the potential to mimic human social intelligence, but most studies focus on static self-report or performance-based tests. |
| Approach: | They propose a framework to assess LLMs' ability to understand and manage intentions by mapping their ability to infer the intentions of others in a game setting. |
| Outcome: | The proposed framework assesses LLMs' ability to understand and manage intentions in a game setting. |
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)
Copied to clipboard
Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang
| Challenge: | Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks. |
| Approach: | They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations. |
| Outcome: | The proposed pipeline can be used to study tool use under three scenarios. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
SimVBG: Simulating Individual Values by Backstory Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have strong human-like capabilities, but rarely simulating individualized human values. |
| Approach: | They propose a framework that simulates individual values based on individual backstories . they use structured data on an individual to transform their backstoried information to a backstory . |
| Outcome: | The proposed framework improves top-1 accuracy by more than 10% over retrieval-augmented generation methods. |
Beyond Static Persona Consistency: Dynamic Persona Coherence in LLM Role-Playing (2026.acl-long)
Copied to clipboard
Yirui QI, Xiaoming Zhang, Ruilin Zeng, Mengyao Liu, Ziyi Zhou, Dezhuang Miao, Bingyu Yan, Zhenyu Guan
| Challenge: | Existing LLMs conflate identity consistency with emotional rigidity . Existing models exhibit either robotic repetition or persona drift . |
| Approach: | They propose a framework that decouples Identity-Layer Stability from Adaptive-Layer Appropriateness to achieve persona coherence repair. |
| Outcome: | Experiments on GPT-4o, Claude-3.5-Sonnet, and DeepSeek-V3.2 show consistent improvements (+16–84% gains) |
Are Your LLMs Capable of Stable Reasoning? (2025.findings-acl)
Copied to clipboard
Junnan Liu, Hongwei Liu, Linchen Xiao, Ziyi Wang, Kuikun Liu, Songyang Gao, Wenwei Zhang, Songyang Zhang, Kai Chen
| Challenge: | Existing evaluation protocols and metrics do not capture the full spectrum of LLM capabilities, especially in complex reasoning tasks. |
| Approach: | They propose a new evaluation metric that continuously assesses model performance across multiple sampling attempts, quantifying both the model’s potential capabilities and operational consistency. |
| Outcome: | The proposed evaluation metric measures model performance across multiple sampling attempts and provides comprehensive insights into their potential capabilities and operational consistency. |
ProMediate: A Simulation Testbed for Evaluating Proactive Mediation in Multi-Party Negotiation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly integrated into agentic frameworks to assist individual users in completing diverse tasks. |
| Approach: | They propose a simulation environment with a plug-and-play proactive AI mediator . they use a socio-cognitive evaluation framework to measure consensus changes, intervention latency, mediator effectiveness and intelligence. |
| Outcome: | The proposed model outperforms a generic baseline in multi-party negotiation scenarios while being 77% faster in response. |
UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | a new benchmark summarization model is being developed to train few-shot summarizers . a large number of summarizing tasks are required to perform well in heterogeneous datasets. |
| Approach: | They propose a few-shot summarization model pre-trained with multiple summarizing tasks . they propose 'uniSumm' to be prefix-tuned to excel at any few-shot summarisation task . |
| Outcome: | The proposed model outperforms baseline models under automatic and human evaluations and achieves comparable results in human evaluation. |
Shadow-Activated Backdoor Attacks on Multimodal Large Language Models (2025.findings-acl)
Copied to clipboard
Ziyi Yin, Muchao Ye, Yuanpu Cao, Jiaqi Wang, Aofei Chang, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
| Challenge: | Existing backdoor attacks on Multimodal Large Language Models are less applicable to open-ended conversations with users. |
| Approach: | They propose a shadow-activated backdoor attack scenario where attackers inject malicious content into the responses of MLLMs when the responses explicitly relate to the shadowed object. |
| Outcome: | The proposed framework achieves the desired behaviors by constructing a poisoned dataset and implementing an attention-regularized tuning strategy. |
AI Sees Your Location—But With A Bias Toward The Wealthy World (2025.emnlp-main)
Copied to clipboard
| Challenge: | Visual Language Models (VLMs) have shown remarkable performance across various tasks, particularly in recognizing geographic information from images. |
| Approach: | They propose to use 1,200 images paired with detailed geographic metadata to evaluate VLMs' performance. |
| Outcome: | The models achieve 53.8% accuracy in city prediction, but exhibit significant biases in regional tasks. |
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation (2026.findings-acl)
Copied to clipboard
Bangde Du, Minghao Guo, Songming He, Ziyi Ye, Xi Zhu, Weihang Su, Shuqi Zhu, Yujia Zhou, Yongfeng Zhang, Qingyao Ai, Yiqun Liu
| Challenge: | Existing studies show that advanced LLMs produce text indistinguishable from human writing. |
| Approach: | They propose a benchmark to assess persona simulation across diverse contexts by decomposing the evaluation into six fundamental capabilities including opinion consistency, memory recall, logical reasoning, persona tone, and syntactic style. |
| Outcome: | The proposed model achieves moderate accuracy but falls short of the basic capabilities needed to simulate personas in real-world contexts. |
MACSum: Controllable Summarization with Mixed Attributes (2023.tacl-1)
Copied to clipboard
Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, Rui Zhang
| Challenge: | Existing work on controllable summarization with mixed attributes lacks designated annotations. |
| Approach: | They propose a human-annotated summarization benchmark for controllable summarizing with mixed attributes based on news and dialogue sources . |
| Outcome: | The proposed dataset contains human-annotated summarization datasets with mixed attributes . hard prompt models yield the best performance on most metrics and human evaluations . mixed-attribute control is still challenging for summarizing tasks . |
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to correct handwritten assignments are to use OCR to recognize characters and compare them to answers. |
| Approach: | They propose a multimodal approach to correct handwritten Chinese characters by combining the visual information of students' handwriting with the encoded representations of answers. |
| Outcome: | The proposed model outperforms OCR-based methods by a large margin. |
ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)
Copied to clipboard
Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang, Ziyi Liu, Haiqin Yang, Yiying Yang, Yuhang Zhao, Pingfu Chao, Wenhao Jiang
| Challenge: | Current Text-to-SQL reasoning models lack integrated execution feedback during generation. |
| Approach: | They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback. |
| Outcome: | The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale. |
Reinforcing Agentic Search Via Reward Density Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic search, but its performance is often hindered by reward sparsity . |
| Approach: | They propose a new research problem to improve the reward obtained per unit of exploration cost by using a system that decomposes long-horizon tasks into intermediate objectives and assigns process-level rewards to provide denser learning signals. |
| Outcome: | The proposed framework outperforms strong baselines on several agentic search benchmarks and achieves comparable performance to that of advanced proprietary models. |
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models (2023.acl-demo)
Copied to clipboard
Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan, Ziyi Liu, Kiran Narahari, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, Xiang Ren
| Challenge: | Existing models are susceptible to learning spurious biases that do not reflect the underlying task. |
| Approach: | They propose an open-source framework for explanation-based model debugging that allows users to provide various forms of feedback on model explanations. |
| Outcome: | The proposed framework improves model’s OOD performance on text classification tasks by up to 18%. |
ER-Test: Evaluating Explanation Regularization Methods for Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Explanation regularization (ER) aims to improve NLM generalization by pushing the NLM’s machine rationales to align with human rationale. |
| Approach: | They propose a framework for evaluating ER models’ OOD generalization along three dimensions: unseen datasets, contrast set tests, and functional tests. |
| Outcome: | The proposed framework evaluates ER models’ OOD generalization across unseen datasets, contrast set tests, and functional tests. |
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents (2026.findings-acl)
Copied to clipboard
Kai Li, Xuanqing Yu, Ziyi Ni, Yi Zeng, Yao Xu, Zheqing Zhang, Xin Li, Jitao Sang, Xiaogang Duan, Xuelei Wang, Chengbao Liu, Jie Tan
| Challenge: | Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, leading to fragmented memories and unstable long-horizon personalization. |
| Approach: | They propose a temporal–hierarchical memory framework that organizes conversations through a Temporal Memory Tree. |
| Outcome: | The proposed framework outperforms baselines while reducing the recalled memory length by 52.20%. |