Papers by Zhang Zeqi

15 papers
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks (2023.findings-acl)

Copied to clipboard

Challenge: Existing work adopts data augmentation techniques to generate pseudo-annotated sentences . existing methods neither preserve semantic consistency of original sentences nor preserve syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.
Approach: They propose a dedicated augmentation technique for relational texts, named GDA, which uses two complementary modules to preserve both semantic consistency and syntax structures.
Outcome: The proposed technique can bring 2.0% F1 improvements in three datasets under low-resource setting.
Making Language Models Better Reasoners with Step-Aware Verifier (2023.acl-long)

Copied to clipboard

Challenge: Large language models have made impressive progress in few-shot learning but still face difficulties in reasoning tasks such as GSM8K.
Approach: They propose a new approach that uses a verifier to filter out incorrect answers based on a weighted voting scheme to improve reasoning ability of language models.
Outcome: The proposed approach improves GSM8K reasoning rate by 17.9% to 58.1%.
PersonaX: A Recommendation Agent-Oriented User Modeling Framework for Long Behavior Sequence (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for user profile modeling extract only partial segments from full historical behavior sequence, resulting in incomplete modeling and suboptimal profiling.
Approach: They propose an agent-agnostic LLM-UM framework to augment downstream recommendation agents . it segments complete historical behaviors into clustered groups and performs offline multi-persona profiling .
Outcome: The proposed framework improves agent performance and inference efficiency by 31% and 10% using 30–50% of behavioral data.
Advancing Process Verification for Large Language Models via Tree-Based Preference Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating step-by-step rationales fail to fully utilize the relative merits of intermediate steps, limiting the effectiveness of feedback provided.
Approach: They propose a tree-based preference learning verifier that constructs reasoning trees via a best-first search algorithm and collects step-level paired data for preference training.
Outcome: The proposed approach outperforms existing benchmarks on arithmetic and commonsense reasoning tasks.
Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are designed as specific task solvers with sophisticated prompt engineering, but are inherently incapacitating to address complex dynamic scenarios.
Approach: They propose an LLM-based agent with policy-level reflection and optimization that can learn from interactive experiences and progressively elevate its behavioral policy.
Outcome: The proposed agent outperforms vanilla LLM and specialized models in blackjack and Texas hold’em.
Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for generating complex semantics and diverse equations are limited by a fixed view.
Approach: They propose a multi-view consistent contrastive learning approach that decouples human reasoning into two independent but consistent views.
Outcome: The proposed approach significantly outperforms existing baselines on complex problems on multiple languages.
Learning Algebraic Recombination for Compositional Generalization (2021.findings-acl)

Copied to clipboard

Challenge: Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks.
Approach: They propose an end-to-end neural model to learn algebraic recombination for compositional generalization.
Outcome: The proposed model is based on two realistic and comprehensive compositional generalization benchmarks.
De-Bias for Generative Extraction in Unified NER Task (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for Named entity recognition (NER) are not consistent with the task, which makes the model vulnerable to incorrect biases.
Approach: They propose to use generative model to recognize entities from sentences . they analyze incorrect biases in the generation process from a causal perspective .
Outcome: The proposed method improves the performance of the generative NER model in various datasets.
An Expression Tree Decoding Strategy for Mathematical Equation Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate mathematical equations from natural language ignore parallel or dependent relations between math expressions.
Approach: They propose to integrate tree structure into the expression-level generation and advocate an expression tree decoding strategy.
Outcome: The proposed method outperforms baseline methods for generating mathematical equations from natural language.
Learning Global Controller in Latent Space for Parameter-Efficient Fine-Tuning (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have shown remarkable performance, but their training costs are exorbitant.
Approach: They propose a parameter-efficient method for exploring optimal solutions within latent space by using latent units to extract input representations from LLMs.
Outcome: The proposed method improves performance on a range of natural language processing tasks.
Query-based Instance Discrimination Network for Relational Triple Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to extract relational triples from open domain texts suffer from error propagation, relation redundancy and lack of high-level connections.
Approach: They propose a query-based approach to construct instance-level representations for relational triples . they use query embeddings and token embeddables to extract all types of triples in one step .
Outcome: The proposed method achieves state-of-the-art on five widely used benchmarks.
PromptNER: Prompt Locating and Typing for Named Entity Recognition (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for prompt learning require a multi-round prompting manner and require elaborate templates.
Approach: They propose to unify entity locating and entity typing into prompt learning by enumerating spans to predict their entity types or constructing type-specific prompts to locate entities.
Outcome: The proposed model outperforms the state-of-the-art model in a few-shot setting . it uses a template filled with multiple prompts and a bipartite graph matching mechanism .
Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition (2021.acl-long)

Copied to clipboard

Challenge: Named entity recognition (NER) is a well-studied task in natural language processing.
Approach: They propose a method that generates span proposals and labels them with categories . they use boundary information of entities and partially matched spans to locate them .
Outcome: The proposed method outperforms state-of-the-art models on nested NER datasets.
How Do In-Context Examples Affect Compositional Generalization? (2023.acl-long)

Copied to clipboard

Challenge: In-context learning paradigms that focus on large corpus are limiting compositional generalization performance.
Approach: They propose a test suite to investigate in-context compositional generalization . they propose to use examples that are structurally similar to the test case .
Outcome: The proposed test suite investigates in-context compositional generalization performance . it finds that the performance can be affected by the selection of in-const examples .
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model (2024.emnlp-main)

Copied to clipboard

Challenge: Using large language models, large multimodal models struggle with basic tasks like reading time from a clock and planning a route using a road map.
Approach: They propose a multimodal self-instruct that synthesizes massive abstract images and visual reasoning instructions.
Outcome: The proposed model synthesizes 11,193 abstract images and reasoning instructions across eight visual scenarios.

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