Papers by Yiwei Li

CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval (2026.findings-acl)

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

Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen, Huangyu Dai, Yiwei Ma, Jiayi Ji, Chenyi Lei, Han Li, Xiaoshuai Sun

Multimodality

Challenge:	Existing approaches to search for images using single-modality are limited by representation space fragmentation.
Approach:	They propose a unified representation framework that achieves efficient query-target alignment . they introduce a multi-level Chain-of-Thought prompting strategy that guides MLMs to generate discriminative, semantically compatible captions for target images .
Outcome:	The proposed framework achieves efficient query-target alignment through synergistic components.

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

Copied to clipboard

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

Control Large Language Models via Divide and Conquer (2024.emnlp-main)

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

Bingxuan Li, Yiwei Wang, Tao Meng, Kai-Wei Chang, Nanyun Peng

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

Challenge:	Lexically Constrained Generation (LCG) is a crucial task of text generation.
Approach:	They propose a Divide and Conquer Generation strategy to enhance LLMs' performance in Lexically Constrained Generation with prompt-based controlling.
Outcome:	The proposed strategy shows 90% improvement on the most challenging LCG task.

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

Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder (2022.findings-emnlp)

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

Bin Sun, Shaoxiong Feng, Yiwei Li, Weichao Wang, Fei Mi, Yitong Li, Kan Li

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection (2023.acl-long)

Challenge:	Existing efforts to identify and avoid CDM to facilitate dialogue learning failed to solve the problem.
Approach:	They propose a Sentence Semantic Segmentation guided Conditional Variational Auto-Encoder which can model and take advantage of the CDM data.
Outcome:	The proposed method can model and take advantages of the CDM data.

Copied to clipboard

Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, Meng Chen

Multimodality

Challenge:	Existing studies focus on fusing different features but ignore the challenge of modality heterogeneity.
Approach:	They propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements and a sentiment-based congruity constraint task to calibrate the feature shift in the representation space.
Outcome:	The proposed model is competitive against existing methods and achieves state-of-the-art results on two public benchmark datasets.

SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking (2025.emnlp-main)

Copied to clipboard

Sifan Li, Yujun Cai, Yiwei Wang

Visual Data in NLP

Challenge:	Vision-language models excel in semantic tasks but fail at detecting hidden content . current architectures prioritize abstract reasoning over low-level visual operations .
Approach:	They propose a benchmark to test vision-language models that can detect hidden content . they propose HC-Bench to scale images to low resolutions to unlock 99% accuracy .
Outcome:	HC-Bench shows that leading VLMs achieve near-zero accuracy even with explicit prompting . et al.: current models prioritize abstract reasoning over low-level visual operations . they urge a shift toward hybrid models bridging gap between computational vision and human cognition .

FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning (2026.findings-acl)

Copied to clipboard

Xiao Li, Bolin Zhu, Kaiwen Shi, Sichen Liu, Yin Zhu, Yiwei Liu, Gong Cheng

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

Challenge:	Existing datasets for numerical reasoning often lack explicit knowledge of formulas . current datasets do not provide process supervision information, resulting in incomplete reasoning .
Approach:	They propose a benchmark for formula-based numerical reasoning with 5,324 questions . they provide annotations in English and Chinese and a formula database as an external knowledge source .
Outcome:	The proposed model includes 5,324 questions requiring calculations grounded in external physics principles.

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.

Vulnerability of LLMs to Vertically Aligned Text Manipulations (2025.acl-long)

Copied to clipboard

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Zhen Xiong, Nanyun Peng, Kai-Wei Chang

Text Classification

Challenge:	Recent research shows that vertical text input significantly degrades the accuracy of large language models (LLMs) in text classification tasks.
Approach:	They investigate the impact of vertical text input on the performance of LLMs . they find that chain of thought reasoning does not help LLM recognize vertical input .
Outcome:	The proposed model can significantly mislead models, posing a risk of bypassing detection in real-world scenarios involving harmful or sensitive information.

Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification (P19-1)

Copied to clipboard

Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li, Yiwei Lv

Information Extraction & Text Mining

Challenge:	Existing approaches to target sentiment analysis are limited by huge search space and sentiment inconsistency.
Approach:	They propose a span-based extract-then-classify framework to detect opinion targets . they propose pipeline, joint, and collapsed models to classify polarities .
Outcome:	The proposed framework outperforms the sequence tagging baseline on three benchmark datasets.

MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision (2021.emnlp-main)

Copied to clipboard

Zheng Li, Danqing Zhang, Tianyu Cao, Ying Wei, Yiwei Song, Bing Yin

Multilinguality

Challenge:	Sequence labeling aims to predict fine-grained sequences of labels for text, but lack of token-level annotated data hinders the effectiveness of supervised methods.
Approach:	They propose a Meta Teacher-Student (MetaTS) Network to alleviate data scarcity by leveraging large multilingual unlabeled data.
Outcome:	The proposed meta learning method alleviates data scarcity by leveraging large multilingual unlabeled data.

Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue (2023.acl-short)

Copied to clipboard

Bin Sun, Yitong Li, Fei Mi, Fanhu Bie, Yiwei Li, Kan Li

Diversifying Neural Dialogue Generation via Negative Distillation (2022.naacl-main)

Challenge:	Existing knowledge-grounded dialogue generation models face the hallucination problem . Existing models generate inappropriate knowledge and generate inconsistent responses .
Approach:	They propose an Augmentative and Contrastive Knowledge Dialogue Expansion Framework to enhance existing knowledge dialogue models by polarizing optimization objectives and weak knowledge generation ability.
Outcome:	The proposed framework expands existing training sets and smooths the optimization objective that enables models to generate ground-truth with or without gold knowledge.

Copied to clipboard

Yiwei Li, Shaoxiong Feng, Bin Sun, Kan Li

HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop (P19-3)

Challenge:	Existing approaches to generate generic responses are ignoring low-frequency but generic responses and bringing low- frequency but meaningless responses.
Approach:	They propose a negative training paradigm that reminds dialogue models not to generate high-frequency responses during training.
Outcome:	The proposed method outperforms previous methods in the generic response problem while minimizing low-frequency but meaningless responses.

Copied to clipboard

Prithviraj Sen, Yunyao Li, Eser Kandogan, Yiwei Yang, Walter Lasecki

Challenge:	HITL-ML approaches are too low-level and far-removed from human’s conceptual models.
Approach:	They propose a prototype HITL-ML system that exposes the machine-learned model through high-level, explainable linguistic expressions formed of predicates representing semantic structure of text.
Outcome:	The proposed system exposes the machine-learned model through high-level, explainable linguistic expressions formed of predicates representing semantic structure of text.

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

To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging (2025.emnlp-main)

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

Zitao Fang, Guodong Du, Shuyang Yu, Yifei Guo, Yiwei Zhang, Yiyao Cao, Jing Li, Ho-Kin Tang, Sim Kuan Goh

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

Challenge:	Existing approaches to model merging ignore the fundamental roles of neurons, connectivity and activation.
Approach:	They propose a framework that relies on neuronal mechanisms to mitigate task interference . they decomposed task-specific representations into two complementary subspaces . their results offer new insights into mitigating task interference and improving knowledge fusion .
Outcome:	The proposed framework reduces task interference within neurons and improves knowledge fusion.

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

Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders (2021.acl-long)

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

Bin Sun, Shaoxiong Feng, Yiwei Li, Jiamou Liu, Kan Li

METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling (2025.acl-long)

Challenge:	Conditional Variational AutoEncoders (CVAE) can enhance the diversity and informativeness of responses in open-domain dialogue generation tasks.
Approach:	They propose a Conditional Variational AutoEncoder (CVAE) that regularizes latent variables and introduces group information to regularize them.
Outcome:	Empirical results show that the proposed model can significantly boost responses in well-established open-domain dialogue datasets.

Copied to clipboard

Bingxuan Li, Yiwei Wang, Jiuxiang Gu, Kai-Wei Chang, Nanyun Peng

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation (2025.emnlp-main)

Challenge:	Chart generation requires strong visual design skills and precise coding capabilities that embed the desired visual properties into code.
Approach:	They propose a vision-language model-based multi-agent framework for effective automatic chart generation.
Outcome:	The proposed framework achieves a 5.2% improvement in the F1 score over the current best chart generation task.

Copied to clipboard

Jiayu Yao, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Yuyao Ge, Zhecheng Li, Xueqi Cheng

Information Retrieval

Challenge:	Existing RAG models are sensitive to the order in which evidence is presented, resulting in unstable performance and biased reasoning.
Approach:	They propose to quantify position bias in multimodal RAG systems by using position sensitivity index . they also develop a visualization framework to trace attention allocation patterns across decoder layers .
Outcome:	The proposed framework shows that multimodal interactions intensify position bias compared to unimodal settings and that this bias increases logarithmically with retrieval range.

DRS: Deep Question Reformulation With Structured Output (2025.findings-acl)

Copied to clipboard

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang

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

Challenge:	Existing models like GPT-3 and Instruct-GPT lack the ability to reformulate unanswerable questions.
Approach:	They propose a zero-shot method that combines the strengths of LLMs with a DFS-based algorithm to iteratively explore potential entity combinations and constrain outputs using predefined entities.
Outcome:	The proposed method outperforms all baselines, including the GPT-3.5 model, on the unanswerable question reformulation task.

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.

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

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

NewsDialogues: Towards Proactive News Grounded Conversation (2023.findings-acl)

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

Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

Natural Language Interfaces

Challenge:	Hot news is one of the most popular topics in daily conversations.
Approach:	They propose a task where a dialogue system can lead the conversation based on key topics of the news.
Outcome:	The proposed method can lead conversations based on key topics of the news . it can also be used in information-seeking and chit-chat scenarios .

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Copied to clipboard

Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang

MoEC: A Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control (2026.acl-long)

Challenge:	Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach:	They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome:	The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

Copied to clipboard

Hui Wu, Chao Xu, Jianghui Wang, Ziqiong Liu, Dong Li, Yiwei Dai, Emad Barsoum

Responsible & Trustworthy NLP

Challenge:	Existing systems rely on a monolithic policy to execute subgoals across varying contexts, causing inconsistent outcomes and scaling only partially mitigates.
Approach:	They propose a memory-routed mixtureof-experts controller for Adaptive Minecraft Control that routes via a subgoal-indexed expert memory and regulates capacity through failure-triggered expert growth and redundancy-aware consolidation.
Outcome:	The proposed controller shows significant gains in adaptability, robustness, and execution consistency over strong baselines.

Generative Dense Retrieval: Memory Can Be a Burden (2024.eacl-long)

Copied to clipboard

Peiwen Yuan, Xinglin Wang, Shaoxiong Feng, Boyuan Pan, Yiwei Li, Heda Wang, Xupeng Miao, Kan Li

Text Clustering

Challenge:	Empirical results show that Generative Dense Retrieval (GDR) achieves an average of 3.0 R@100 improvement on NQ dataset under multiple settings and has better scalability.
Approach:	They propose a Generative Dense Retrieval paradigm that auto-decodes document identifiers given a query and uses memory to avoid memory confusion.
Outcome:	Empirical results show that the proposed paradigm improves on the small-scale corpora and improves scalability.

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

Responsible & Trustworthy NLP

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.

Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation (2024.findings-acl)

Copied to clipboard

Yiwei Li, Fei Mi, Yitong Li, Yasheng Wang, Bin Sun, Shaoxiong Feng, Kan Li