Papers by Yang Sui

26 papers
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing large language model (LLM) agents are unable to adapt to changing domain knowledge and rules.
Approach: They propose an LLM agent framework that continuously learns updated domain knowledge at test time.
Outcome: The proposed agent improves on a customer due diligence name screening task on . the agent learns updated domain knowledge at test time.
SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine (2025.findings-naacl)

Copied to clipboard

Challenge: Multi-hop Question Answering (MHQA) is a challenging task that requires models to answer multiple questions with multiple passages.
Approach: They propose a self-guided prompting finite state machine to improve multi-hop reasoning abilities by iterating over multiple questions and correcting itself to improve accuracy.
Outcome: The proposed approach outperforms baselines on Musique and other datasets.
Towards Fine-grained Text Sentiment Transfer (P19-1)

Copied to clipboard

Challenge: Existing methods for fine-grained text sentiment transfer only reverse the sentiment polarity of text, but they lack a robust and parallel learning algorithm.
Approach: They propose a novel fine-grained text sentiment transfer task that revises a sequence to satisfy a given sentiment intensity while preserving the original semantic content.
Outcome: The proposed model outperforms existing methods by a large margin in automatic evaluation and human evaluation.
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach: They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome: The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.
Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information (2024.lrec-main)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting and large language models (LLMs) have shown great potential in improving performance on challenging reasoning tasks.
Approach: They propose a new metric which extends the concept of pointwise V-information to black-box models and quantifies label-relevant new information introduced by CoT prompting.
Outcome: The proposed metric extends the concept of pointwise V-information to black-box models, quantifying label-relevant new information introduced by CoT prompting beyond pre-existing label information.
Towards Comprehensive Description Generation from Factual Attribute-value Tables (P19-1)

Copied to clipboard

Challenge: Existing models for comprehensive descriptions for factual attribute-value tables might suffer from missing key attributes and groundless information problems.
Approach: They propose a force attention method to encourage the generator to pay more attention to uncovered attributes to avoid potential key attributes missing.
Outcome: The proposed model outperforms the state-of-the-art baselines on automatic and human evaluation.
Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones? (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive capabilities, but still suffer from inconsistency issues.
Approach: They develop a ConsisEval benchmark to evaluate LLMs' inconsistency . they find that LLM models can paradoxically fail at easier problems .
Outcome: The proposed model achieves highest consistency score but inconsistent to specific questions due to distraction by redundant information, misinterpretation of questions, etc.
Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to improve self-correction performance of Large Language Models are based on intrinsic selfcorrectione, which allows the model to check and revise its selfgenerated answers without external feedback.
Approach: They propose to decompose the self-correction capability into confidence and critique capabilities and a metric for overall self-corretion capability evaluation.
Outcome: The proposed method outperforms vanilla SFT and achieves much higher accuracy after self-correction.
Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach: STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome: STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach: They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome: The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.
Pun-GAN: Generative Adversarial Network for Pun Generation (D19-1)

Copied to clipboard

Challenge: Existing methods for generating pun sentences with word senses lack large-scale corpus for supervised learning . a pun is a clever and amusing use of a word with two meanings (word senses)
Approach: They propose an adversarial generative network for pun generation with a generator and a discriminator to distinguish between generated pun sentences and real sentences with specific word senses.
Outcome: The proposed network generates sentences that are more ambiguous and diverse in both automatic and human evaluation.
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters.
Approach: They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance.
Outcome: The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios.
MoE-I2: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition (2024.findings-emnlp)

Copied to clipboard

Challenge: emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models.
Approach: They propose a two-stage compression method tailored for Mixture of Experts to reduce the model size and decrease the computational cost.
Outcome: The proposed method reduces model size and improves inference efficiency while maintaining performance in various zero-shot tasks.
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs.
Approach: They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn.
Outcome: The proposed framework improves strategy selection preferences at each dialogue turn.
Can Large Multimodal Models Uncover Deep Semantics Behind Images? (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies on visual deep semantics focus primarily on superficial description of images, revealing a notable deficiency in the systematic investigation of the inherent deep semantic.
Approach: They propose a benchmark to assess Large Multimodal Models’ (LMMs) capacities of visual deep semantics.
Outcome: The proposed benchmark demonstrates a substantial gap between the deep semantic comprehension capabilities of existing LMMs and humans.
Document-level Event Extraction via Parallel Prediction Networks (2021.acl-long)

Copied to clipboard

Challenge: Document-level event extraction (DEE) is indispensable when events are described throughout a document.
Approach: They propose a document-level event extraction model that can extract structured events from a text in parallel.
Outcome: The proposed model outperforms current state-of-the-art methods on a document-level event extraction task.
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Copied to clipboard

Challenge: Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach: They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome: The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.
A Probabilistic Inference Scaling Theory for LLM Self-Correction (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated the capability to refine their generated answers through self-correction, enabling continuous performance improvement over multiple rounds.
Approach: They propose a probabilistic theory to model the dynamics of accuracy change and explain performance improvements observed in multi-round self-correction.
Outcome: The proposed model can predict accuracy curves and improve accuracy over multiple rounds.
Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have recently gained the In-Context Learning ability . however, the quality of demonstration examples is usually uneven .
Approach: They propose to determine optimal weights for demonstration examples and apply them during ICL.
Outcome: The proposed approach outperforms conventional ICL on 8 classification tasks.
Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have a high inference latency stemming from autoregressive decoding.
Approach: They propose a novel decoding paradigm that drafts multiple tokens and verifies them in parallel . they aim to provide a catalyst for further research on Speculative Decoding .
Outcome: The proposed method drafts multiple tokens and verifies them in parallel . it can be used to accelerate inference in large language models.
Learning to Control the Fine-grained Sentiment for Story Ending Generation (P19-1)

Copied to clipboard

Challenge: Existing studies focus on controlling the sentiment of story endings.
Approach: They propose a generic and novel framework which controls fine-grained sentiment intensity for automatic story ending generation without manually annotating sentiment labels.
Outcome: The proposed framework can generate story endings which meet the given sentiment intensity better.
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions.
Approach: They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary.
Outcome: The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy.
M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data.
Approach: They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them.
Outcome: The proposed method improves visual generality performance on knowledge data of different granularities.
Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation (2021.naacl-main)

Copied to clipboard

Challenge: Existing definition generation methods take the source word as an indecomposable semantic unit, but in parataxis languages like Chinese, word meanings can be composed using the word formation process.
Approach: They propose to use word formation features to enhance Definition Generation (DG) in Chinese to generate an explanatory text.
Outcome: The proposed model enhances Definition Generation (DG) in Chinese by decomposing the word meaning into different semantic components.
CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)

Copied to clipboard

Challenge: Large foundation models have become huge, but they consume computational resources in pretraining.
Approach: They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training.
Outcome: The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime.
Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scenarios.
Approach: They propose to select a representative subset of in-context demonstrations that can prompt different test instances in a specific task.
Outcome: The proposed method can be used to generate representative in-context demonstrations.

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