Papers by Yifei Yu

21 papers
Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation (2026.findings-acl)

Copied to clipboard

Challenge: Current approaches for Multimodal Sentiment Analysis (MSA) rely on parameter-heavy LLMs for classification, overlooking multimodal sentiment reasoning generation in resource-limited environments.
Approach: They propose a multimodal sentiment reasoning distillation model that employs a teacher-assistant-student paradigm to address deployment constraints in resource-limited environments.
Outcome: The proposed model performs well on a resource-limited JMSRC task with only 3B parameters and shows generalization and interpretability.
Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for idea generation either trivially prompt LLMs or expose LLM to extensive literature without indicating useful information.
Approach: They propose a chain-of-ideas agent that organizes literature in a chains structure . they propose evaluating idea-generation methods from different perspectives .
Outcome: The proposed agent outperforms existing methods and matches human quality in idea generation.
Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks and evaluation protocols focus on surface-level factual recall.
Approach: They propose a benchmark for assessing cognitive memory under cue–trigger semantic disconnect.
Outcome: The proposed framework reveals failures not captured by existing benchmarks.
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Challenge: Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach: AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome: Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .
Towards Provably Secure Generative AI: Reliable Consensus Sampling (2026.findings-acl)

Copied to clipboard

Challenge: Existing research on generative AI security is driven by mutually reinforcing attack and defense methodologies grounded in empirical experience.
Approach: They propose a new algorithm that uses a random sampling algorithm to control risk.
Outcome: The proposed algorithm improves robustness and utility while maintaining latency comparable to existing algorithms.
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer (2025.acl-long)

Copied to clipboard

Challenge: Foundational models and their checkpoints have advanced deep learning, boosting performance across applications.
Approach: They propose a method for pruning fine-tuned models by calculating differences between them and original model.
Outcome: The proposed method can improve performance across vision, NLP, and multi-modal benchmarks.
Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to improve the reliability of Large Language Models (LLMs) in clinical applications require factual knowledge from open-ended datasets and clinical case-based knowledge to provide context grounded in real-world patient experiences.
Approach: They propose a retrieval-augmented generation framework based on the electronic health record to offer contextual information from other patients’ discharge reports.
Outcome: The proposed framework outperforms a text-based ranker in a clinical QA dataset with 1,280 discharge-related questions .
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models have underscored their exceptional reasoning prowess with natural language understanding across a broad spectrum of tasks.
Approach: They examine whether Large Language Models actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks.
Outcome: The proposed model improves reasoning performance while suppressing it leads to notable degradation.
VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy (2026.findings-eacl)

Copied to clipboard

Challenge: Large language models (LLMs) have been widely deployed in Conversational AIs . however, the methods proposed in the study rely on a white-box setting .
Approach: They propose an indirect prompt injection attack that induces privacy extraction in LLMs . they use token-efficient data containing false memories to inject LLM data .
Outcome: The proposed method outperforms baselines and achieves state-of-the-art performance.
RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing research has focused on role-playing agents’ ability to portray specified characters, but their ability to advance the plot requires substantial improvements to deliver more engaging interaction.
Approach: They propose a role-playing framework to evaluate and enhance the plot-progression capabilities of role-players.
Outcome: The proposed framework improves RPAs’ ability to time plot developments and yields a significant increase in conversation turns and sustained higher arousal levels.
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)

Copied to clipboard

Challenge: Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities.
Approach: They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts.
Outcome: The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs.
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach: They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome: The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.
To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging (2025.emnlp-main)

Copied to clipboard

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.
Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods to enhance credibility and verifiability of large language models (LLMs) mainly focus on passage-level or paragraph-level references or citations, which fall short in verifikatability.
Approach: They propose a method that provides sentence-level citations in LLM-generated responses.
Outcome: The proposed method achieves 90% accuracy in long-form question-answering tasks.
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for process-oriented math reward models rely on manual annotation.
Approach: They propose a process-oriented math process reward model called Math-shepherd which assigns a reward score to each step of math problem solutions.
Outcome: The proposed model breaks the bottleneck of manual supervision in two scenarios.
Pretraining Language Models with Text-Attributed Heterogeneous Graphs (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing pretraining tasks for Language Models (LMs) focus on learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs.
Approach: They propose a topology-aware pretraining task that explicitly considers the topological and heterogeneous information in TAHGs by optimizing an LM and an auxiliary heterogenous graph neural network.
Outcome: The proposed framework explicitly considers the topological and heterogeneous information in TAHGs.
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)

Copied to clipboard

Challenge: AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery.
Approach: They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows.
Outcome: The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages.
Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models? (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in handling long sequences have unlocked new possibilities for long-context in-contact learning (ICL).
Approach: They investigate how increased examples influence predictive uncertainty . they quantify uncertainty across different “shot” configurations and focus on EU .
Outcome: The proposed model reduces uncertainty in simple and complex tasks by injecting task-specific knowledge.
Knowledge Fusion By Evolving Weights of Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Experimental results on mainstream language models show that Evolver outperforms previous state-of-the-art models by large margins due to the high training costs of large language models.
Approach: They propose a method to integrate multiple models from diverse training scenarios into a unified model.
Outcome: The proposed method outperforms state-of-the-art models on mainstream language models by large margins.
Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models (2025.acl-long)

Copied to clipboard

Challenge: Multiple-choice question answering (MCQA) is widely used to assess the understanding capability of Large Multimodal Models (LMMs).
Approach: They propose a task to evaluate the robust understanding capability of Large Multimodal Models (LMMs) they introduce a benchmark to assess performance across various ability dimensions .
Outcome: The proposed model can withhold answers when encountering unsolvable problems of MCQA, proving it understands the answer.
BERT-BC: A Unified Alignment and Interaction Model over Hierarchical BERT for Response Selection (2024.lrec-main)

Copied to clipboard

Challenge: Recent performance boosting for dialogue response selection task achieved by Cross-Encoder based models is limited and the learned models have poor generalization capability in realistic scenarios.
Approach: They propose a model that combines the representation-based Bi-Encoder and interaction-based Cross-Encoding to achieve better semantic representation.
Outcome: The proposed model can achieve state-of-the-art performance on three benchmark datasets for multi-turn response selection.

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