Papers by Yifan Sun

30 papers
WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings (2023.acl-long)

Copied to clipboard

Challenge: Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art.
Approach: They propose a whitening-based contrastive learning method for sentence embedding learning which combines contrastive and shuffled group whitening.
Outcome: The proposed method achieves better alignment and uniformity on seven semantic textual similarity tasks.
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework (2025.acl-long)

Copied to clipboard

Challenge: Existing evaluation metrics for RAG systems are lacking due to high costs of data construction and lack of factual accuracy.
Approach: They propose a framework to evaluate RAG systems in specialized scenarios . they propose three new metrics to evaluate LLM-generated responses .
Outcome: The proposed framework outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation (2026.findings-acl)

Copied to clipboard

Challenge: Motivational interviewing (MI) is a directive, client-centered counseling approach for eliciting clients' motivation for behavioral change.
Approach: They propose a multi-LLM agent framework for controllable MI dialogue generation . therapist and client agents generate MI-coded utterances guided by MI codes .
Outcome: The proposed framework can generate fluent dialogues with minimal intervention time and a high level of evaluation.
KARL: Reinforcement Learning for LLM Agents on Multi-Turn Knowledge-Intensive Agentic Tasks (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models have shown remarkable potential as autonomous agents, but their effectiveness in knowledge-intensive tasks remains limited by passive knowledge utilization.
Approach: They propose a framework that enables LLM agents to dynamically explore structured knowledge sources through multi-turn interactions.
Outcome: The proposed framework outperforms existing retrieval-augmented approaches on knowledge graph and database tasks while maximizing tool-use behaviors end-to-end.
Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs? (2024.naacl-long)

Copied to clipboard

Challenge: Existing large language models lack knowledge of nuanced, domain-specific details and are susceptible to hallucinations.
Approach: They construct a benchmark that measures head, torso, and tail facts in terms of popularity.
Outcome: The proposed model is based on 18K question-answer pairs regarding head, torso, and tail facts in terms of popularity.
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach: They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome: Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.
AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach: They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome: The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning (2025.emnlp-main)

Copied to clipboard

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.
Parallel sentences mining with transfer learning in an unsupervised setting (2021.naacl-srw)

Copied to clipboard

Challenge: Existing methods to mine parallel sentences in low-resource environments are not suitable for many low-level language pairs.
Approach: They propose an approach based on transfer learning to mine parallel sentences in an unsupervised setting using bilingual corpora of low-resource language pairs.
Outcome: The proposed model improves the performance of mined parallel sentences at two real-world low-resource language pairs compared with previous methods.
Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework (2026.eacl-industry)

Copied to clipboard

Challenge: Existing methods for fact-checking lack coherence and context, whereas abstractive methods lack cohesion and context.
Approach: They propose a framework that generates Chinese user-specific debunking passages . they propose to use a generative AI framework to generate context-sensitive responses .
Outcome: The proposed framework generates Chinese user-specific debunking passages by iteratively refining outputs based on simulated user feedback.
Controlling Styles in Neural Machine Translation with Activation Prompt (2023.findings-acl)

Copied to clipboard

Challenge: Earlier studies on controlling styles in neural machine translation (NMT) have focused on regulating the level of formality, but they still encounter two major challenges.
Approach: They propose a method to control the style of neural machine translation by retrieving prompts from stylized monolingual corpus.
Outcome: The proposed method can control the style of translation and achieve remarkable performance.
A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends (2026.findings-acl)

Copied to clipboard

Challenge: Visually Rich Document Understanding (VRDU) frameworks are a key area of research . early approaches to VRDU relied on manually crafted rules and domain-specific heuristics . conventional deep learning approaches do not integrate the diverse modalities in documents .
Approach: They review recent advances in MLLM-based Visually Rich Document Understanding (VRDU) their findings highlight emerging trends and promising research directions .
Outcome: The proposed frameworks are scalable, reliable, and adaptable, the authors argue . their findings highlight emerging trends and promising research directions .
The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas (2025.emnlp-main)

Copied to clipboard

Challenge: Existing evaluations of LLMs' moral reasoning capabilities rely on single-step evaluations, ignoring how models adapt to evolving ethical challenges.
Approach: They propose a framework to evaluate evolving moral judgments of large language models (LLMs) using multi-step moral dilemma questionnaires.
Outcome: The proposed framework enables a fine-grained analysis of how LLMs adjust their moral reasoning across escalating dilemmas.
AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing studies on Android agents lack systematic research on open-source and closed-source models.
Approach: They propose a framework for Android agents that includes an operation environment and a reproducible benchmark.
Outcome: The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM.
UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents (2026.acl-long)

Copied to clipboard

Challenge: Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images.
Approach: They propose a benchmark to evaluate the performance of Large Multimodal Models (LMMs) using a constrained-category KIE track and an open-categorical KIE Track.
Outcome: Experiments on 15 state-of-the-art LMMs show performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios.
TopoSHIELD: Reshaping the Flow of Malice via Spatio-Temporal Risk-Aware Topological Evolution in Multi-Agent Systems (2026.findings-acl)

Copied to clipboard

Challenge: Multi-agent systems (MAS) inherit general task-solving and instruction-following capabilities, but their interconnectivity introduces significant security risks.
Approach: They propose a framework that reshapes the flow of malice via risk-aware topological evolution.
Outcome: Empirically, TopoSHIELD reduces toxicity by 58% on GPT-4o while preserving high utility (>90% success rate).
DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are pre-trained on vast datasets composed of billions of tokens harvested from diverse text sources.
Approach: They propose a data engineering method to refine the pretraining corpus through data rating, tagging and editing.
Outcome: The proposed method improves the quality of the pretraining corpus by enhancing 100 billion tokens of the training corpus.
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach: They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome: The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.
Audio-centric Video Understanding Benchmark without Text Shortcut (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in multimodal large language models (MLLMs) focus on visual abilities, but audio is essential for video understanding.
Approach: They propose an audio-centric video understanding benchmark to evaluate video comprehension capabilities of multimodal LLMs with a particular focus on auditory information.
Outcome: The proposed video understanding benchmarks evaluate video comprehension capabilities of multimodal models with a particular focus on auditory information.
LEAF: Large Language Diffusion Model for Time Series Forecasting (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work has applied large language models (LLMs) into time series forecasting, but they lack an understanding of holistic temporal patterns with potential error accumulation.
Approach: They propose a framework that marries Larg e Langu age Diffusion Model with time series forecasting (LEAF) they propose converting time series into tokens and adopting language diffusion models to capture temporal dependencies.
Outcome: The proposed framework generates future predictions with a diffusion model from a holistic view.
User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems (2025.acl-industry)

Copied to clipboard

Challenge: Large Language Models (LLMs) can be used to broaden user experiences beyond established preferences and reinforce feedback loops.
Approach: They propose a hierarchical approach that combines hierarchic planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty.
Outcome: The proposed approach shows significant gains in both user satisfaction and exploration diversity.
HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)

Copied to clipboard

Challenge: a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models .
Approach: They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams .
Outcome: The proposed model is based on o1-like models and a high-level model.
SPO: Self Preference Optimization with Self Regularization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing reference-free preference optimization methods exhibit higher training efficiency but are prone to overoptimization, leading to performance degradation.
Approach: They propose a reference-free preference optimization method that replaces the logsigmoid loss function with a SiLU function to improve the model's performance.
Outcome: The proposed method achieves 7% improvement over SimPO on AlpacaEval 2 and MT-Bench.
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies (2026.findings-acl)

Copied to clipboard

Challenge: Existing research has proposed a variety of training-free and post-training methods for selecting critical key-value pairs at each generation step.
Approach: They propose to use local (sliding-window) and global (compression/selective) attention across layers to enlarge long-context modeling.
Outcome: Experiments on models from 340M to 1.3B parameters show that the proposed method matches or exceeds full attention and native sparse attention in both common-sense reasoning and long-context understanding tasks.
Won’t Get Fooled Again: Answering Questions with False Premises (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are often easily deceived by tricky questions such as “How many eyes does the sun have?” .
Approach: They annotate a FalseQA dataset containing 2365 human-written FPQs and find that PLMs are capable of discriminating FPqs by fine-tuning on moderate numbers.
Outcome: The proposed model can discriminate on FPQs by fine-tuning on moderate numbers of examples and generate reasonable explanations for false premise questions.
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach: They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome: The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.
OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability.
Approach: They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability.
Outcome: Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA.
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks (2026.findings-acl)

Copied to clipboard

Challenge: Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications.
Approach: They propose a framework that retrieves context from a memory bank to enhance alignment . they propose EMI-based approach to align vision and language models .
Outcome: The proposed framework reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead.
Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery (2025.findings-acl)

Copied to clipboard

Challenge: Existing concepts-based explainable approaches do not discover unseen concepts . a recent approach to solve this problem is concept-based explanations .
Approach: They propose a framework that extracts comprehensible concepts automatically with no annotations . ECO-Concept uses an object-centric architecture to extract task-specific semantic concepts .
Outcome: a new framework extracts comprehensible concepts with no concept annotations . the proposed framework outperforms existing methods in computability tests on diverse tasks .
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks.
Approach: They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset.
Outcome: The proposed model performs well across tasks and languages.

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