Papers by Zhuoran Wang

16 papers
A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation (C18-1)

Copied to clipboard

Challenge: Existing methods to generate responses using beam search focus on current optimal results.
Approach: They propose a beam search method that uses a Prospective-Performance Network to predict the future reward of a partially-generated response.
Outcome: The proposed method can increase the quality and diversity of generated responses with high inference efficiency.
Self-Renewal Prompt Optimizing with Implicit Reasoning (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in NLP have been driven by the development of Large Language Models (LLMs).
Approach: They propose a self-renewal approach to optimize LLM outputs to better align with human preferences without supervised fine-tuning.
Outcome: The proposed approach improves outputs to better align with human preferences across LLMs and tasks without supervised fine-tuning.
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning (2024.acl-long)

Copied to clipboard

Challenge: Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).
Approach: They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM.
Outcome: The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%.
MULFE: A Multi-Level Benchmark for Free Text Model Editing (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have impressive capabilities in comprehending human language and vast parametric knowledge obtained from large corpora.
Approach: They propose a multi-level benchmark for free text model editing to bridge the gap . they categorize probe queries into three levels of generalization .
Outcome: The proposed method improves the generalization performance of large langugae models.
CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)

Copied to clipboard

Challenge: Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge.
Approach: They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge.
Outcome: The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.
COMPKE: Complex Question Answering under Knowledge Editing (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for knowledge editing do not accurately evaluate how well models apply knowledge in real-life situations.
Approach: They propose a benchmark to evaluate how well updated models apply new knowledge in real-life situations.
Outcome: The proposed method achieves 39.47 accuracy on GPT-4o-mini but drops significantly to 3.83 on Qwen2.5-3B.
LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) often exhibit poor performance on knowledge-intensive tasks, such as commonsense reasoning.
Approach: They propose a method to elicit, filter and integrate knowledge in large language models (LINKED) they propose 'reward model' to filter out noisy knowledge and 'take marginal consistent reasoning module'
Outcome: The proposed method outperforms SOTA baselines on two commonsense reasoning tasks.
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains.
Approach: They propose a data composition framework that allows LLMs to enhance their multi-domain capabilities during supervised fine-tuning.
Outcome: The proposed framework improves multi-domain fostering performance by 29.77% compared to uniform weights.
Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio (2026.acl-long)

Copied to clipboard

Challenge: Recent multimodal large language models lack robust audio-visual integration ability and performance on DeafTest is highly correlated with AV-Odyssey accuracy.
Approach: They propose a benchmarking tool that integrates audio-visual reasoning with audio-video cues to infer solutions.
Outcome: The proposed model performs well on DeafTest, but lacks audio perception in simple audio tasks.
MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach: They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome: The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.
Enhancing Multilingual Reasoning via Steerable Model Merging (2026.findings-acl)

Copied to clipboard

Challenge: Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model.
Approach: They propose a model merging framework that modulates the contribution of each source model.
Outcome: Experiments show that the proposed model merging framework outperforms strong baselines on multilingual reasoning benchmarks across 21 different languages.
LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics (N18-1)

Copied to clipboard

Challenge: Existing evaluation metrics for NRG models can't measure semantic relevance and diversity of generated results.
Approach: They propose a large-scale domain-specific conversational corpus with preprocessing and cleansing procedures for model training and a testing set for measuring the diversity of generated results.
Outcome: The proposed corpus can be taken as a new benchmark dataset for the NRG task.
CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet (2021.acl-demo)

Copied to clipboard

Challenge: CogNet is a knowledge base that integrates three types of knowledge: linguistic knowledge, world knowledge and commonsense knowledge.
Approach: They propose an information extraction toolkit called CogIE that is a bridge connecting raw texts and CogNet.
Outcome: The proposed toolkit can ground raw texts to CogNet and leverage different types of knowledge to enrich extracted results.
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence.
Approach: They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics .
Outcome: The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate .
AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in deep learning have significantly impacted the legal domain.
Approach: They propose a multi-agent framework for judicial decision-making that simulates the court trial process . they propose 420 Chinese judgment documents to support their framework and build a large-scale legal knowledge base .
Outcome: The proposed framework outperforms existing methods in various aspects, especially in generating legal articles.
VC4VG: Optimizing Video Captions for Text-to-Video Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in text-to-video generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos.
Approach: They propose a caption optimization framework tailored to the needs of T2V models.
Outcome: The proposed framework improves video caption quality and video generation performance.

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