Papers by Zhe Peng

7 papers
LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Reinforcement learning with verifiable rewards (RLVR) is a key technique for enhancing LLMs’ reasoning abilities, yet its data inefficiency remains a major bottleneck.
Approach: They propose a gradient-alignment-based method which intelligently selects the learnable and representative training reasoning data for RLVR post-training.
Outcome: Experiments on five reasoning benchmarks show that the proposed method significantly reduces training data requirements while improving performance.
AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Copied to clipboard

Challenge: Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach: They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome: The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.
Hyperbolic Hierarchy-Aware Knowledge Graph Embedding for Link Prediction (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge graph embedding methods are built on Euclidean space, which are difficult to handle hierarchical structures.
Approach: They propose a KGE model with extended Poincaré Ball and polar coordinate system to capture hierarchical structures.
Outcome: The proposed model captures hierarchical relationships with extended Poincaré Ball and polar coordinate system in hyperbolic space and achieves state-of-the-art results on part of link prediction tasks.
Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)

Copied to clipboard

Challenge: Existing models lack the ability to adhere to instructions, resulting in suboptimal performance.
Approach: They propose an automated iterative instruction-following benchmark with integrated feedback mechanism.
Outcome: The proposed benchmark identifies erroneous components in model responses and provides feedback accurately.
SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored.
Approach: They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios.
Outcome: The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios.
FastBERT: a Self-distilling BERT with Adaptive Inference Time (2020.acl-main)

Copied to clipboard

Challenge: Pre-trained language models like BERT have proven to be highly performant, but are often computationally expensive in many practical scenarios.
Approach: They propose a speed-tunable FastBERT with adaptive inference time that can be flexibly adjusted under varying demands.
Outcome: The proposed model achieves promising results in English and Chinese datasets.
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach: They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome: The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

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