Papers by Yicheng Wang

22 papers
TellWhisper: Tell Whisper Who Speaks When (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches decouple temporal modeling and speaker modeling when addressing 'when' and 'who' . a new framework that couples temporal structure with speaker dynamics is proposed to address these limitations .
Approach: They propose a framework that couples temporal and speaker identity within the speech encoder . they propose TS-RoPE, a time-speaker rotary positional encoding that partitions Query/Key channels into temporal, speaker subspaces and applies region-specific rotations to align "when" and "who" cues in selfattention.
Outcome: The proposed framework couples temporal structure with speaker dynamics in speech encoder . it uses frame-level speaker activity to estimate speaker-activity estimates .
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)

Copied to clipboard

Challenge: Named Entity Recognition models are feature-engineering and machine learning based.
Approach: They propose a new NER learning framework that uses entity mentions to improve model performance.
Outcome: The proposed model achieves better performance on OOV entities on various settings and datasets.
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach: They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome: The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)

Copied to clipboard

Challenge: Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications.
Approach: They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter.
Outcome: Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation.
RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Copied to clipboard

Challenge: RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach: They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome: The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.
Bayesian Calibration of Win Rate Estimation with LLM Evaluators (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) show the potential of using LLMs as evaluators for text quality evaluation.
Approach: They propose two methods to improve the accuracy of LLM evaluators by Bayesian inference.
Outcome: The proposed methods improve the accuracy of the win rate estimation using LLMs . the proposed methods are based on six datasets covering story generation, summarization, and instruction following tasks .
Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for candidate answer extraction are reliant on linguistic rules or annotated data and face partial annotation issue and challenges in generalization.
Approach: They propose an unsupervised approach that leverages the inherent structure of context passages through a Differentiable Masker-Reconstructor (DMR) Model with the enforcement of self-consistency for picking up salient information tokens.
Outcome: The proposed model outperforms supervised and unsupervised methods in two datasets with exhaustively-annotated answers and shows that it is comparable to supervised methods.
ConQuer: A Framework for Concept-Based Quiz Generation (2025.naacl-srw)

Copied to clipboard

Challenge: Existing concepts-based quiz generation frameworks that leverage external knowledge sources are challenging and labor intensive.
Approach: They propose a concept-based quiz generation framework that leverages external knowledge sources to assess the quality of the generated quizzes, using LLMs as judges.
Outcome: The proposed framework shows a 4.8% improvement in evaluation scores and a 77.52% win rate in pairwise comparisons against baseline quiz sets.
LAMBDA: Large Language Model-Based Data Augmentation for Multi-Modal Machine Translation (2024.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal machine translation methods are underperforming compared to pre-trained models due to lack of triplet training data.
Approach: They propose a multi-modal machine translation method that integrates images and visual modality to enhance language understanding.
Outcome: The proposed method can enrich the original samples and expand the dataset without requiring external images and text.
DHP Benchmark: Are LLMs Good NLG Evaluators? (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
Approach: They propose a framework that measures the discernment of Large Language Models (LLMs) across diverse NLG tasks.
Outcome: The proposed framework provides quantitative discernment scores for LLMs across four NLG tasks.
Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation (2026.findings-acl)

Copied to clipboard

Challenge: Multi-agent systems (MAS) are increasingly used for open-ended idea generation . when and why collective interaction expands the solution space remains unclear .
Approach: They propose to study diversity in multi-agent systems across three bottom-up levels: model intelligence, agent cognition, and system dynamics.
Outcome: The proposed model yields diminishing diversity despite higher quality . the proposed model fails to expand diversity and causes it to collapse .
Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation (2024.acl-long)

Copied to clipboard

Challenge: Abductive reasoning is the process of making educated guesses to provide explanations for observations.
Approach: They propose a task of complex logical hypothesis generation to generate a complex logique hypothesis that can explain a set of observations.
Outcome: The proposed model generates logical hypotheses closer to the reference hypothesis, but not better on unseen observations.
BalanceSFT: Improving LLM Function Calling with Balanced Training Signals and Data Hardness (2026.findings-acl)

Copied to clipboard

Challenge: Currently, Supervised Fine-Tuning (SFT) is the prevailing method for equipping Large Language Models (LLMs) with function calling capabilities, but its effectiveness is often compromised by two challenges: 1) lengthy Chain-of-Thought (CoT) reasoning tokens dominate training signals over concise function calls in the learning objective; 2) scarcity of hard training examples.
Approach: They propose a framework that uses a self-adjusted signal balancing loss and a hard data re-sampling strategy to selectively generate new, high-quality complex data guided by model errors.
Outcome: The proposed framework surpasses state-of-the-art models like GPT-5 in function calling performance.
Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models that understand image and text but also cross-reference in-between are lacking in evaluation data resources.
Approach: They propose a multimodal evaluation pipeline to automatically generate question-answer pairs to test models’ understanding of the visual scene, text, and related knowledge.
Outcome: The proposed model can answer the highly semantic VCR question correctly but fails to answer related visual question (Q2), textual question (q3), and background knowledge question ( Q4) as shallow mappings with language priors and unbalanced utilization of information between modalities.
LLaMA-Rider: Spurring Large Language Models to Explore the Open World (2024.findings-naacl)

Copied to clipboard

Challenge: Recent studies have used Large Language Models to help decision-making and planning in environments, but their capacity to acquire environmental knowledge and adapt in an open world remains uncertain.
Approach: They propose an approach to spur LLMs to explore the open world, gather experiences, and learn to improve their task-solving capabilities by using a feedback-revision mechanism.
Outcome: The proposed model enhances the efficiency of the LLM in exploring the open world and improves its ability to accomplish more tasks through fine-tuning with merely 1.3k instances of collected data, showing minimal training costs compared to baseline using reinforcement learning.
Commonsense for Generative Multi-Hop Question Answering Tasks (D18-1)

Copied to clipboard

Challenge: Reading comprehension QA tasks have seen a recent surge in popularity, yet most work has focused on fact-finding extractive QA.
Approach: They propose a multi-hop generative task that uses a pointer-generator decoder to synthesize disjoint pieces of information within the context to generate an answer.
Outcome: The proposed model performs better than previous generative models and is competitive with current state-of-the-art span prediction models.
Mixed Distillation Helps Smaller Language Models Reason Better (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent large language models (LLMs) have demonstrated impressive multiple step-by-step reasoning capabilities in recent NLP reasoning tasks.
Approach: They propose a mixed distillation framework that distills multiple step-by-step reasoning abilities into smaller language models (SLMs) they leverage LLMs to generate multiple step by step reasoning rationales by sampling automatically.
Outcome: The proposed framework outperforms existing models on SVAMP, GSM8K and ASDIV, while a single model generated by MD exceeds the comprehensive performance of two individual CoT and PoT distilled models.
Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have examined dataset biases in VQA benchmarks with short-phrase answers Multiple-choice Question with the LONG Answers (VCR, VLEP, etc.)
Approach: They propose to use Adversarial Data Synthesis (ADS) to generate synthetic training and debiased evaluation data and introduce Intra-sample Counterfactual Training (ICT) to assist models in utilizing synthesized training data.
Outcome: The proposed approach improves model performance even in domain-shifted scenarios.
Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents (2022.findings-acl)

Copied to clipboard

Challenge: Existing text semantic matching models do not provide granularity for text comparison.
Approach: They propose a simple yet effective training strategy for text semantic matching by disentangling keywords from intents.
Outcome: The proposed approach achieves stable performance improvements against a wide range of models on three benchmarks.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.
Robust Machine Comprehension Models via Adversarial Training (N18-2)

Copied to clipboard

Challenge: Existing models for the Stanford Question Answering Dataset suffer from a 50% decrease in F1 score during adversarial evaluation based on AddSent.
Approach: They propose an alternative adversary-generation algorithm, AddSentDiverse, that significantly increases the variance within the adversarial training data by providing effective examples that punish the model for making certain superficial assumptions.
Outcome: The proposed algorithm can achieve a 36.5% increase in F1 score while maintaining performance on the regular SQuAD task.
See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for video understanding suffer from autoregressive generation of tokens.
Approach: They propose a training-free loosely SD framework for Video-LLMs that uses visual-relevant tokens to accurately pinpoint the latter.
Outcome: The proposed framework boosts the accepted length and speedup ratio by 136% and 35% compared to SOTA training-free SD methods for Video-LLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations