Papers by Zhengyang Wang

26 papers
Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog (2023.acl-industry)

Copied to clipboard

Challenge: Existing methods for analyzing textual attributes in product catalogs are not effective on structured tabular data since they are trained on free-form natural language texts.
Approach: They propose a model to handle error detection over tabular data following a pre-training paradigm.
Outcome: The proposed model improves on a real-world Amazon Product Catalog table by 16% over state-of-the-art methods and by 11% on PR AUC over attribute value validation task.
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Parallel reasoning enhances Large Reasoning Models but incurs prohibitive costs due to futile paths caused by early errors.
Approach: They propose a systematic taxonomy of path pruning to categorize methods by signal source and learnability.
Outcome: The proposed model improves LRMs but incurs prohibitive costs due to futile paths caused by early errors.
DPTDR: Deep Prompt Tuning for Dense Passage Retrieval (2022.coling-1)

Copied to clipboard

Challenge: Recent studies show that prompt tuning is unfriendly for industrial deployment in dense retrieval tasks.
Approach: They propose to apply prompt tuning to dense retrieval tasks to reduce deployment cost . they propose to use retrieval-oriented intermediate pretraining and unified negative mining .
Outcome: The proposed method outperforms state-of-the-art models on MS-MARCO and Natural Questions.
DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools .
Approach: They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression .
Outcome: The proposed approach outperforms human experts in medical examinations on diverse datasets.
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)

Copied to clipboard

Challenge: Retrieval-augmented Large Language Models struggle with complex inputs and noisy knowledge retrieval hindering model effectiveness.
Approach: They propose a query generation method that integrates query generation blending with knowledge filtering to enhance retrieval-augmented LLMs.
Outcome: The proposed approach surpasses state-of-the-art benchmarks on open-domain question answering benchmarks.
SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents (2024.acl-long)

Copied to clipboard

Challenge: Existing studies on building language agents have not addressed this social learning gap.
Approach: They propose an interactive learning method that improves the social intelligence of language agents by using behavior cloning and self-reinforcement based training on filtered social interaction data.
Outcome: The proposed method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent) without the loss of more generic abilities, such as the ability to answer knowledge-based questions.
ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations (2025.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks for recommendation explanation evaluation lack item diversity and user preferences data.
Approach: They propose a model-agnostic recommendation explanation evaluation benchmark based on Amazon e-commerce categories with implicit preferences . they propose two novel automatic evaluators that enable scalable and human-preference aligned evaluation of explanations .
Outcome: The proposed model-agnostic evaluation benchmark outperforms existing methods in a variety of domains.
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Copied to clipboard

Challenge: Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach: They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome: The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges (2026.findings-acl)

Copied to clipboard

Challenge: Increasing saturation of web data limits further scaling of model intelligence.
Approach: They propose a benchmark to evaluate machine creativity in code generation that combines combinatorial and exploratory creativity through reverse engineering and self-play.
Outcome: The proposed benchmark targets combinatorial and exploratory creativity through reverse engineering and self-play.
Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach: They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome: The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to embed knowledge graphs have ignored the fact that they contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities.
Approach: They propose a novel geometric representation that jointly embeds the two views of a KG using dual geometric representations.
Outcome: Experiments on the public DBpedia KG and a newly-created industrial KG show the proposed method works well.
UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)

Copied to clipboard

Challenge: Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses.
Approach: They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy.
Outcome: The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy.
Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

Copied to clipboard

Challenge: Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach: They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome: The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.
Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have emerged as a promising avenue for time series forecasting . existing approaches face limitations such as marginalized role in model architectures and lack of interpretability.
Approach: They propose a framework that exploits LLM causal reasoning to discover and use directed causal associations among covariates.
Outcome: The proposed model improves predictive accuracy while yielding transparent, traceable reasoning about variable interactions.
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach: They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome: The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Copied to clipboard

Challenge: In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach: They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome: The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.
Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)

Copied to clipboard

Challenge: Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements.
Approach: They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness.
Outcome: Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency.
Data Diversity Matters for Robust Instruction Tuning (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities.
Approach: They propose an algorithm to control diversity and quality of instruction tuning datasets and validate it.
Outcome: The proposed algorithm significantly improves worst and average case performance on large scale instruction tuning datasets.
Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Deception and persuasion play a critical role in long-horizon multi-party dialogues, especially when the interests, goals, and motivations of the participants are not aligned.
Approach: They propose a game in which players must determine each other’s hidden identities to complete their team’s objective.
Outcome: The proposed model can be used to determine the true player identities of six human players in a cooperative-competitive game.
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.
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach: They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome: The proposed framework outperforms baseline methods in real-time and in real applications.
TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) can solve complex tasks through iterative information retrieval.
Approach: They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards .
Outcome: Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models.
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization (2026.acl-long)

Copied to clipboard

Challenge: Existing quantization methods for large language models suffer performance degradation at ultra-low bit-widths due to key cache outliers.
Approach: They propose a vector quantization method that suppresses outliers in the key cache and reduces memory access overhead.
Outcome: The proposed method outperforms baseline quantization methods across long-context understanding and mathematical reasoning tasks while minimizing memory access overhead.
SCOTT: Self-Consistent Chain-of-Thought Distillation (2023.acl-long)

Copied to clipboard

Challenge: Large language models (LMs) generate free-text rationales for their predictions via chain-of-thought prompting, but there is little guarantee that the generated rationale is consistent with LM’s predictions or faithfully justify the decisions.
Approach: They propose a faithful knowledge distillation method to learn a small, self-consistent CoT model from a larger teacher model by contrastive decoding.
Outcome: The proposed method yields comparable performance but is less faithful than baselines.
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach: They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome: The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.
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.

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