Papers by Feng Mao
CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025.emnlp-main)
Copied to clipboard
| Challenge: | a number of tools are used to perform complex tasks, but the tool utilization process can cause errors. |
| Approach: | They propose a critique evaluation benchmark for tool learning that analyzes function-calling errors on tool evaluation benchmarks. |
| Outcome: | The proposed critique evaluation benchmark holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios. |
LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation (2022.tacl-1)
Copied to clipboard
| Challenge: | Existing benchmarks for natural language processing focus on understanding or generating short texts . lack of standardized benchmarks makes it difficult to assess and compare models . |
| Approach: | They propose a story-centric benchmark for Chinese long text modeling that aggregates two understanding tasks and two generation tasks. |
| Outcome: | The proposed model outperforms similar-sized models on understanding and generation tasks. |
Closed Boundary Learning for Classification Tasks with the Universum Class (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods treat the Universum class equally with the classes of interest, leading to problems such as overfitting, misclassification, and diminished model robustness. |
| Approach: | They propose a closed boundary learning method that applies closed decision boundaries to classes of interest and designates the area outside all closed boundaries as the Universum class. |
| Outcome: | The proposed method improves accuracy and robustness of classification models on six state-of-the-art tasks. |
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for zero-shot text classification lack prompt engineering due to prompt brittleness . however, these methods are not effective for zero shot text classifications . |
| Approach: | They propose a method that predicts token probabilities across multiple positions and simulates comprehensive sampling of generation paths in a single run of a language model. |
| Outcome: | The proposed approach improves accuracy and reduces standard deviation by 98% . it maintains comparable performance even without a prompt, reducing the need for prompt engineering . |
FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Controllable text generation (CTG) focuses on crafting texts adhering to specific attributes . studies show learning-based methods require extensive computational and data resources . |
| Approach: | They propose a learning-free approach that dynamically adjusts the weights of selected feedforward neural network vectors to steer the outputs of large language models. |
| Outcome: | The proposed approach outperforms learning-based and learning-free methods on multi-attribute control. |
Rethinking Prompt Optimizers: From Prompt Merits to Optimization (2026.eacl-long)
Copied to clipboard
Zixiao Zhu, Hanzhang Zhou, Zijian Feng, Tianjiao Li, Chua Jia Jim Deryl, Lee Onn Mak, Gee Wah Ng, Kezhi Mao
| Challenge: | Existing methods to optimize prompts rely on LLMs' self-generation ability but lack interpretability due to implicit optimization. |
| Approach: | They propose a model-agnostic prompt quality merits and a merit-guided, locally deployable prompt optimizer trained on a lightweight LLM to improve prompt quality. |
| Outcome: | The proposed model avoids online optimization, reduces privacy concerns, and generalizes effectively to both large-scale and lightweight inference models. |
Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning (2025.naacl-long)
Copied to clipboard
| Challenge: | Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language models (LLMs). |
| Approach: | They propose a logit separability-based method that integrates multiple class-related words into each sample-label pair to improve LLM understanding. |
| Outcome: | The proposed method improves ICL performance by providing clearer instructions and richer label information. |
Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for dialog routing are mostly heuristic and cannot achieve high-quality performance. |
| Approach: | They propose a multi-task learning framework with a dialog encoder and two tailored gated mechanism modules to solve this problem. |
| Outcome: | The proposed model can play the role of hierarchical information filtering and is non-invasive to existing dialog systems. |
EDEntail: An Entailment-based Few-shot Text Classification with Extensional Definition (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for few-shot text classification use either class labels or intensional definitions of class labels for label semantics expression. |
| Approach: | They propose a method that employs extensional definition of class labels in hypotheses and then order and format them into a sequence to form hypothese . |
| Outcome: | The proposed method surpasses supervised-learning methods and prompt-based methods on five classification datasets and is comparable to state-of-the-art models. |
LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction (2024.acl-long)
Copied to clipboard
| Challenge: | In-context learning (ICL) is an emerging ability of large-scale labeled data for document-level event argument extraction (EAE). |
| Approach: | They propose an explicit heuristic-driven demonstration construction approach that emphasizes task heurs in document-level event argument extraction tasks. |
| Outcome: | The proposed method outperforms existing prompting methods and few-shot supervised learning methods on document-level EAE datasets. |
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. |
PromptExplainer: Explaining Language Models through Prompt-based Learning (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing explanation methods rely on linear approximations, accentuating irrelevant input tokens. |
| Approach: | They propose a method that aligns the explanation process with the masked language modeling task of pretrained language models and leverages prompt-based learning to generate class-dependent explanations. |
| Outcome: | Extensive experiments show that PromptExplainer outperforms state-of-the-art explanation methods. |
MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation (2026.acl-long)
Copied to clipboard
Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang, Jinxing Zhou, Changsen Yuan, Tian Lan, Ziqin Zhou, Yudong Li, Jiajun Xu, Jingyun Liao, YiMing Cheng, Xuefeng Chen, Xian-Ling Mao, Yousheng Feng
| Challenge: | Existing evaluation benchmarks for text-to-audio-video (T2AV) generation are largely designed for human-recorded videos or single-speaker settings. |
| Approach: | They propose a failure-driven diagnostic benchmark for multi-talker dialogue-centric audio-video generation. |
| Outcome: | The benchmark evaluates multi-speaker dialogue generation at four levels: audio-visual signal fidelity, temporal attribute consistency, social interaction, and cinematic expression. |
Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing video QA models lack the capacity for deep video understanding and flexible multistep reasoning. |
| Approach: | They propose a video question answering model which performs dynamic multistep reasoning between questions and videos. |
| Outcome: | The proposed model improves on three widely used video QA datasets and displays better interpretability by backtracing along with the attention mechanisms to the video scene graphs. |
APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models (2023.emnlp-main)
Copied to clipboard
Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu
| Challenge: | Existing prompt tuning methods only introduce prompts at the input layer, limiting performance and leaving large room for improvement. |
| Approach: | They propose a method that involves tuning a small set of soft prompts for pre-trained language models. |
| Outcome: | The proposed method outperforms state-of-the-art methods with pre-trained models on the SuperGLUE benchmark. |
MDCSpell: A Multi-task Detector-Corrector Framework for Chinese Spelling Correction (2022.findings-acl)
Copied to clipboard
| Challenge: | Chinese Spelling Correction (CSC) is a task to detect and correct misspelled characters in Chinese texts. |
| Approach: | They propose a general detector-corrector multi-task framework which exploits the visual and phonological features of the misspelled characters and minimizes their misleading impact on the context. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on Chinese Spelling Correction tasks. |
OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics (2021.acl-long)
Copied to clipboard
Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang
| Challenge: | Existing automatic metrics are observed to correlate poorly with human evaluation. |
| Approach: | They propose to use OpenMEVA to evaluate open-ended story generation metrics. |
| Outcome: | The proposed test suite assesses the capabilities of open-ended story generation metrics on annotated stories and auto-constructed test examples. |
Unveiling the Art of Heading Design: A Harmonious Blend of Summarization, Neology, and Algorithm (2024.findings-acl)
Copied to clipboard
| Challenge: | Creating an appealing heading is crucial for attracting readers and marketing work or products. |
| Approach: | They propose a benchmark to measure the quality of heading generation using summarization, neology, and algorithm metrics. |
| Outcome: | The proposed benchmark compared 6,653 abstracts with corresponding descriptions and acronyms and found that it excels across summarization, neology, and algorithm aspects. |
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training (2023.findings-emnlp)
Copied to clipboard
Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa
| Challenge: | Several perspectives of robustness for pre-trained language models have been studied independently, but lacking a unified consideration in multiple perspectives. |
| Approach: | They propose a technique to enhance the multi-perspective robustness of LMs by introducing adversarial perturbation while the model parameters are selectively updated upon their relative importance. |
| Outcome: | The proposed technique improves the robustness of LMs by incorporating four perspectives on model robustness. |
STRUDEL: Structured Dialogue Summarization for Dialogue Comprehension (2022.emnlp-main)
Copied to clipboard
Borui Wang, Chengcheng Feng, Arjun Nair, Madelyn Mao, Jai Desai, Asli Celikyilmaz, Haoran Li, Yashar Mehdad, Dragomir Radev
| Challenge: | Abstractive dialogue summarization is an important standalone task in natural language processing, but no previous work has explored whether it can be used to boost an NLP system's performance on other important dialogue comprehension tasks. |
| Approach: | They propose a novel type of dialogue summarization task that decomposes and imitates the hierarchical, systematic and structured mental process that human beings usually go through when understanding and analyzing dialogues. |
| Outcome: | The proposed model improves the performance of transformer encoder language models on two important dialogue comprehension tasks. |
LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence (2026.findings-acl)
Copied to clipboard
Wenjin Liu, Haoran Luo, Xin Feng, Xiang Ji, Lijuan Zhou, Rui Mao, Jiapu Wang, Shirui Pan, Erik Cambria
| Challenge: | Existing benchmarks for legal general intelligence (GI) are result-oriented and do not evaluate the legal intelligence of large language models (LLMs). |
| Approach: | They propose a Chinese legal benchmark for evaluating legal GI in large language models . they use recent legal cases and exam questions to create multiple-choice questions . |
| Outcome: | The proposed benchmarks lack a systematic evaluation of the legal intelligence of large language models (LLMs) the results show that even the best LLMs lagging behind human legal professionals. |