Papers by Yao Pan

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Challenge:	Existing supervised models struggle to make correct predictions on rare word senses due to limited training data.
Approach:	They propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge.
Outcome:	The proposed method outperforms previous methods on both frequent and rare word senses.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models (2024.findings-acl)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Tongshuang Wu, Jianshu Chen

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)

Challenge:	Existing studies on the confidence calibration of LLMs have not explored the effects of different prompting strategies on LLM performance.
Approach:	They propose Fact-and-Reflection prompting which improves LLM confidence calibration . they propose to use human cognition to elicit known "facts" and ask model to "reflect" over them .
Outcome:	The proposed method lowers the expected calibration error by 23.5% on multi-purpose QA tasks.

Copied to clipboard

Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

DetGPT: Detect What You Need via Reasoning (2023.emnlp-main)

Challenge:	Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty.
Approach:	They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples.
Outcome:	The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance.

Copied to clipboard

Renjie Pi, Jiahui Gao, Shizhe Diao, Rui Pan, Hanze Dong, Jipeng Zhang, Lewei Yao, Jianhua Han, Hang Xu, Lingpeng Kong, Tong Zhang

How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)

Challenge:	Recent advances in the field of computer vision have enabled more effective and sophisticated interactions between humans and machines.
Approach:	They propose a reasoning-based object detection paradigm that leverages state-of-the-art multi-modal models and open-vocabulary object detectors to perform reasoning within the context of the user’s instructions and the visual scene.
Outcome:	The proposed method enables users to interact with the system using natural language instructions, allowing for a higher level of interactivity.

Copied to clipboard

Wenlin Yao, Lifeng Jin, Hongming Zhang, Xiaoman Pan, Kaiqiang Song, Dian Yu, Dong Yu, Jianshu Chen

C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References (2022.acl-short)

Challenge:	Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence.
Approach:	They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation.
Outcome:	The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models.

Copied to clipboard

Xiang Yue, Xiaoman Pan, Wenlin Yao, Dian Yu, Dong Yu, Jianshu Chen

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Challenge:	Existing approaches to pretrain open-domain question answering systems lack task-specific annotations.
Approach:	They propose to pretrain a two-stage open-domain question answering system with strong transfer capabilities by using a dictionary and a large-scale corpus.
Outcome:	The proposed approach leads to 2%-10% gains in top-20 accuracy and improves with reader.

Copied to clipboard

Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Challenge:	Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach:	They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome:	This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Challenge:	In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations.
Approach:	They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention .
Outcome:	The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.

Copied to clipboard

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

Green & Sustainable NLP

Challenge:	Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach:	They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome:	The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation (2024.acl-long)

Copied to clipboard

Xinglin Wang, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrieval (2026.acl-demo)

Challenge:	Existing methods to improve output quality without aggregating input tokens are limited by the complexity of aggregation of responses.
Approach:	They propose to extract and integrate segment-level commonalities from candidate samples to enhance performance of LLMs in open-ended and reasoning tasks.
Outcome:	The proposed method improves performance on reasoning, code generation and mathematical reasoning tasks without requiring additional models and overlooking the knowledge present among the candidates.

Copied to clipboard

Shuheng Chen, Namratha Patil, Haonan Pan, Angel Hsing-Chi Hwang, Yao Du, Ruishan Liu, Jieyu Zhao

CrowdSelect: SyntheticInstruction Data Selection with Multi-LLM Wisdom (2026.findings-eacl)

Challenge:	MED-COPILOT is an interactive research prototype for evidence-aware clinical reasoning . large language models (LLMs) are prone to hallucinations and lack verifiable evidence grounding .
Approach:	They propose a system that integrates GraphRAG and semantic-keyword similar-patient retrieval to support transparent clinical reasoning.
Outcome:	The proposed system outperforms baseline and standard RAGs on clinical note completion and medical question answering.

Copied to clipboard

Yisen Li, Lingfeng Yang, Wenxuan Shen, Pan Zhou, Yao Wan, Weiwei Lin, Dongping Chen

Machine Translation

Challenge:	Existing methods for capturing instruction-following complexity rely on single-dimensional signals, but they fail to capture complexity across diverse fields.
Approach:	They propose three foundational metrics that leverage Multi-LLMs wisdom to capture instruction-response pair characteristics and propose CrowdSelect, an integrated metric incorporating a clustering-based approach to maintain response diversity.
Outcome:	The proposed metrics outperform existing models on MT-bench and Arena-hard and show improvements of 4.81% on full and LoRA fine-tuning.

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning (2025.emnlp-main)

Copied to clipboard

Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs (2025.findings-emnlp)

Challenge:	Existing reward models assume a global reward function, limiting personalization and pluralistic alignment.
Approach:	They propose a framework that leverages binary preference datasets to enhance personalized preference learning.
Outcome:	The proposed framework captures diverse human preferences without fine-grained annotations and significantly improves personalized preference learning on downstream tasks.

Copied to clipboard

Yao Fu, Runchao Li, Xianxuan Long, Haotian Yu, Xiaotian Han, Yu Yin, Pan Li

Challenge:	Neural network pruning disrupts LLMs’ internal activation features crucial for lie detection . layer-wise pruning sparsity inadvertently removes crucial weights, failing to improve lie detection performance despite its reliance on the most crucial LLM layer.
Approach:	They propose a pruning approach that places greater emphasis on layers with more activation outliers and stronger discriminative features simultaneously.
Outcome:	The proposed approach improves the hallucination detection for pruned LLMs (achieving 88% accuracy at 50% sparsity) and enhances their performance on TruthfulQA.

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Copied to clipboard

Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Green & Sustainable NLP

Challenge:	Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach:	They propose a method that conducts customized evaluation tailored to each target model.
Outcome:	The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation (2025.acl-long)

Copied to clipboard

Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Liu Weichuan, Lei Hou, Juanzi Li

Information Retrieval

Challenge:	Adaptive Retrieval-Augmented Generation (RAG) is an effective strategy to alleviate hallucination of large language models (LLMs).
Approach:	They propose a novel adaptive RAG model that extracts self-aware uncertainty of large language models from their internal states and invokes retrieval accordingly.
Outcome:	The proposed model outperforms existing adaptive RAG methods on complex and simple Question Answering datasets.

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning (2024.naacl-long)

Copied to clipboard

Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu

FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have achieved remarkable success in aligning with user intentions.
Approach:	They develop local and global explanation methods and a feed-forward-based method for input-output attribution to investigate the impact of instruction tuning on user intentions.
Outcome:	The proposed method compares explanations from pre-trained and instruction-tuned models . it empowers LLMs to recognize the instruction parts of user prompts, it encourages response generation .

Copied to clipboard

Runchao Li, Yao Fu, Mu Sheng, Xianxuan Long, Haotian Yu, Pan Li

CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models (2026.findings-acl)

Challenge:	Current compression strategies, including token eviction and learned projections, often lead to biased representations and may require costly model retraining.
Approach:	They propose a training-free KV cache compression framework that equalizes the contribution of all tokens to the compressed representation.
Outcome:	The proposed framework ensures unbiased information retention in the KV cache.

Copied to clipboard

Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong, Wang Zhen, Yongjie Wang, Yao Pan

Operation-guided Neural Networks for High Fidelity Data-To-Text Generation (D18-1)

Challenge:	Existing classification-based methods capture noise and spurious correlations while overlooking the underlying causal mechanisms.
Approach:	They propose a hallucination detection framework based on structural causal models that captures static and passive signals from internal states and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise.
Outcome:	Experiments on four datasets and three widely used LLMs show that the proposed framework improves AUROC and interpretability.

Copied to clipboard

Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong Pan, Chin-Yew Lin

Text Generation

Challenge:	Recent neural models for data-to-text generation generate descriptions that are not consistent with structured data.
Approach:	They propose a framework for data-to-text generation that uses symbolic operations to generate texts from structured data.
Outcome:	The proposed framework improves the fidelity of the generated texts to the input structured data.

ASD-iLLM:An Intervention Large Language Model for Autistic Children based on Real Clinical Dialogue Intervention Dataset (2025.findings-emnlp)

Copied to clipboard

Shuzhong Lai, Chenxi Li, Junhong Lai, Yucun Zhong, Chenyu Yan, Xiang Li, Haifeng Li, Gang Pan, Lin Yao, Yueming Wang

When Truthful Representations Flip Under Deceptive Instructions? (2025.emnlp-main)

Challenge:	Currently, leveraging large language models (LLMs) for autism intervention is a significant yet challenging task, especially when directly employing LLMs as an intervention doctor.
Approach:	They propose a framework for training LLMs to conduct dialogue interventions in accordance with the principles of Applied Behavior Analysis (ABA) they also propose 'role-play' strategy in which LLM act as autistic children to comprehensively evaluate the doctor model's capabilities at the dialogue level.
Outcome:	The proposed framework outperforms existing models in both automatic and human evaluation, with intervention strategies and dialogue style more closely resembling those of clinical intervention doctors.

Copied to clipboard

Xianxuan Long, Yao Fu, Runchao Li, Mu Sheng, Haotian Yu, Xiaotian Han, Pan Li

Representation Learning

Challenge:	Large language models (LLMs) follow maliciously crafted instructions to generate deceptive responses, posing safety challenges.
Approach:	They use Sparse Autoencoders to analyze LLM's internal representations to determine when and how they "flip" from truthful to deceptive under deceptively crafted instructions.
Outcome:	The proposed model's True/False output is predictable across all conditions based on the model''s representation, and the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations.

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency (2026.acl-long)

Copied to clipboard

Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang

Challenge:	Existing evaluations rely on point-wise confidence, which can mask brittle belief.
Approach:	They propose a measure of belief robustness that evaluates coherence across a conceptual neighborhood.
Outcome:	The proposed model is more resistant to interference than existing models.

CogLM: Tracking Cognitive Development of Large Language Models (2025.naacl-long)

Copied to clipboard

Xinglin Wang, Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, but few studies have explored the reasons behind the evolutionary relationship among various abilities.
Approach:	They construct a benchmark CogLM based on Piaget's Theory of Cognitive Development (PTC) which measures the cognitive levels of Large Language Models (LLMs) using 1,220 questions spanning 10 cognitive abilities crafted by more than 20 human experts.
Outcome:	The proposed framework provides a comprehensive testbed for the cognitive levels of LLMs.

Copied to clipboard

Batu Guan, Yao Wan, Zhangqian Bi, Zheng Wang, Hongyu Zhang, Pan Zhou, Lichao Sun

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) have shown significant potential in code generation, but they also present challenges regarding the protection of Intellectual Property (IP) related to model architectures, weights, and training data.
Approach:	They propose a multi-bit watermarking technique that embeds additional information to preserve provenance details, such as the vendor ID of an LLM.
Outcome:	The proposed technique preserves provenance details while maintaining syntactical correctness of generated code.

What’s Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs (2025.findings-emnlp)

Copied to clipboard

Jinhao Pan, Chahat Raj, Ziyu Yao, Ziwei Zhu

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Challenge:	Existing benchmarks evaluate bias by term-based mode, but they fail to capture hidden biases in nuanced settings.
Approach:	They propose a dataset to assess bias at the semantic level that bias concepts are hidden within naturalistic, subtly framed contexts in real-world scenarios.
Outcome:	The proposed dataset shows that models reduce bias in response at term level, but reinforce bias in nuanced settings.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao

MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification (2025.findings-acl)

Challenge:	Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach:	They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome:	Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.

Copied to clipboard

xu Zhao Pan, Pengfei Zhou, Jiaxin Ai, Wangbo Zhao, Kai Wang, Xiaojiang Peng, Wenqi Shao, Hongxun Yao, Kaipeng Zhang

Multimodality

Challenge:	Existing benchmarks of large language models focus on error detection, neglecting other scenarios like reasoning search.
Approach:	et al. propose a multi-task, multimodal benchmark to assess effectiveness of PRMs . step correctness, answers aggregation and reasoning process search are evaluated . ethical principles of MPBench are based on a set of evaluation paradigms based in a text-based benchmark .
Outcome:	a new benchmark assesses the effectiveness of large language models (LLMs) in multiple scenarios . it uses three evaluation paradigms to assess the effectiveness and compares them with existing models . a the proposed model improves reasoning accuracy by providing stepwise feedback for multi-step reasoning results .

MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning (2024.lrec-main)

Copied to clipboard

Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu

Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Challenge:	Existing methods focus on specializing LMs in mathematical reasoning and rely on knowledge distillation.
Approach:	They propose a multi-view fine-tuning method that exploits existing mathematical problem datasets with diverse annotation styles.
Outcome:	The proposed method outperforms existing methods that rely heavily on LLM teachers . it grants models generalization ability across views and datasets, and the capability to learn from inaccurate or incomplete data.

Copied to clipboard

Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Zero-shot Entity Linking with Efficient Long Range Sequence Modeling (2020.findings-emnlp)

Challenge:	Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach:	They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome:	The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.

Copied to clipboard

Zonghai Yao, Liangliang Cao, Huapu Pan

A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation (P19-1)

Challenge:	Existing methods to expand the long-range sequence modeling require expensive pre-training.
Approach:	They propose a method to expand the long-range sequence modeling without retraining the BERT model.
Outcome:	The proposed method improves the STOA on the zero-shot entity linking dataset by 76.06% and for long data by 74.57%.

Copied to clipboard

Feng Nie, Jin-Ge Yao, Jinpeng Wang, Rong Pan, Chin-Yew Lin

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding (2022.findings-emnlp)

Challenge:	Recent neural language generation systems often hallucinate contents when trained on loosely corresponding pairs of the input structure and text.
Approach:	They propose to integrate a language understanding module for data refinement with self-training iterations to induce strong equivalence between the input data and the paired text.
Outcome:	Experiments on the E2E challenge dataset show that the proposed framework reduces relative unaligned noise by 50% compared with the current state-of-the-art ensemble generator.

Copied to clipboard

Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, Zeyu Xiong

Multimodality

Challenge:	Existing methods for temporal sentence grounding ignore two crucial issues . 1) Boundary-bias: the video downsampling process may lose these two frames . 2) Reasoning-biases: such incorrect new boundary frames lead to the reasoning bias .
Approach:	They propose a siamese sampling mechanism to generate additional contextual frames . they use a reasoning strategy to learn the inter-relationship among these frames a .
Outcome:	Extensive experiments demonstrate the effectiveness of a new siamese sampling network on three challenging datasets.

The Impact of Large Language Models in Academia: from Writing to Speaking (2025.findings-acl)

Copied to clipboard

Mingmeng Geng, Caixi Chen, Yanru Wu, Yao Wan, Pan Zhou, Dongping Chen

S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation (2026.findings-acl)

Challenge:	Large language models (LLMs) are impacting human society, especially in textual information.
Approach:	They propose to build an automated monitoring platform to track the impact of large language models on human expression.
Outcome:	The results show that LLM-style words such as significant are used more frequently in abstracts and oral presentations.

Copied to clipboard

Yu Pan, Xiongfei Wu, Yang Yuguang, Jixun Yao, Maxime Cordy, Lei Ma, Jianjun Zhao

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce (N19-2)

Challenge:	S2ST-Omni integrates a speech-to-text frontend with a modular, plug-and-play text-tospeech backend.
Approach:	They propose a compositional S2ST framework that integrates a speech-to-text frontend with a modular, plug-and-play text-tospeech backend.
Outcome:	The proposed framework outperforms existing frameworks in translation and synthesis . it integrates a speech-to-text translation frontend with a plug-and-play text-tospeech backend .

Copied to clipboard

Jianguo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu

Robustness in NLP

Challenge:	Existing methods for short product title generation only consider textual information from long titles . MM-GAN incorporates image information and attribute tags from product, as well as textual info from original long titles.
Approach:	They propose a multi-modal generative adversarial network for short product title generation in E-commerce . they incorporate image information and attribute tags from product, as well as textual information from original long titles .
Outcome:	The proposed model outperforms state-of-the-art methods on a large-scale E-commerce dataset.

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Copied to clipboard

Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li

Challenge:	Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach:	They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome:	The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.

Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling (2025.acl-long)

Copied to clipboard

Yang Yuguang, Yu Pan, Jixun Yao, Xiang Zhang, Jianhao Ye, Hongbin Zhou, Lei Xie, Lei Ma, Jianjun Zhao

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Challenge:	Expressive zero-shot voice conversion (VC) aims to modify source timbre to match unseen speaker . existing zero- shot VC systems struggle to reproduce paralinguistic information in highly expressive speech .
Approach:	They propose a framework for expressive zero-shot voice conversion that uses hybrid content encoding and memory-augmented context-aware timbre modeling.
Outcome:	The proposed framework surpasses state-of-the-art VC systems in speech naturalness, speaker similarity, and speaker similarness.

Copied to clipboard

Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Reinforced Dynamic Reasoning for Conversational Question Generation (P19-1)

Challenge:	Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach:	They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome:	The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.

Copied to clipboard

Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun

Natural Language Interfaces

Challenge:	Empirical results on the recently released CoQA dataset demonstrate the effectiveness of our method . large-scale highquality conversational question answering datasets such as CoQA and QuAC can help train models to answer sequential questions.
Approach:	They propose a task called Conversational Question Generation which generates a question based on a passage and a conversation history to generate the next question.
Outcome:	The proposed method is based on a question-answering style conversation dataset . it can be used to generate meaningful questions on QA and SQuAD datasets .

Prompt Refinement with Image Pivot for Text-to-Image Generation (2024.acl-long)

Copied to clipboard

Jingtao Zhan, Qingyao Ai, Yiqun Liu, Yingwei Pan, Ting Yao, Jiaxin Mao, Shaoping Ma, Tao Mei

Multilinguality

Challenge:	Recent advances in text-to-image generation have markedly expanded the boundaries of digital artistry, enabling the creation of visually compelling images with unprecedented ease.
Approach:	They propose to decompose the prompt refinement process into two tasks: inferring user-preferred images from user languages and translating them into system languages.
Outcome:	Experiments show that PRIP outperforms baselines and transfers to unseen systems in a zero-shot manner.

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency (2024.findings-acl)

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs (2025.emnlp-main)

Challenge:	evaluating superLLMs is especially difficult because of their intelligence-intensive nature.
Approach:	They propose an evaluation benchmark with accurate labels for SuperLLMs whose capabilities surpass those of humans . they first prove that consistency between model under evaluation and reference model can equalize the true capabilities of the model to be evaluated .
Outcome:	The proposed evaluation benchmarks can assess the true capabilities of the model to be evaluated without accurate labels.

Copied to clipboard

Yao Fu, Xianxuan Long, Runchao Li, Haotian Yu, Mu Sheng, Xiaotian Han, Yu Yin, Pan Li