Papers by Haoyi Zhou

4 papers
Towards Objective Fine-tuning: How LLMs’ Prior Knowledge Causes Potential Poor Calibration? (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have enabled powerful domain-specific applications through supervised fine-tuning.
Approach: They propose a cognition-aware framework that applies targeted learning strategies according to the model’s prior knowledge to improve calibration.
Outcome: The proposed framework significantly improves calibration while maintaining performance, achieving an average 57% reduction in ECE compared to standard fine-tuning in Llama3-8B.
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (2022.findings-acl)

Copied to clipboard

Challenge: enabling pre-trained models inference on ciphertext data is difficult due to the complex computations in transformer blocks.
Approach: They propose an approximation approach for transformers which enables inference on ciphertext data.
Outcome: The proposed approach can infer pre-trained models on encrypted data with negligible performance drop but enjoy theory-guaranteed privacy-preserving advantage.
Path Spuriousness-aware Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning (2023.eacl-main)

Copied to clipboard

Challenge: Multi-hop reasoning is a common approach for query answering, but can be biased to spurious paths which coincidentally lead to the correct answer with poor explanation.
Approach: They propose a method that quantitatively estimates to what extent a path is spurious by a metric called Path Spuriousness (PS) they propose KG reasoning, which infers new facts along existing paths in KGs.
Outcome: The proposed model significantly improves the agent’s ability to prevent spurious paths while keeping comparable to state-of-the-art performance.
Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks or datasets require only a few steps of reasoning, making it difficult to analyse AI’s behaviour with reference to different problems within a specific topic in detail.
Approach: They propose a conic10K math problem dataset that requires only a few steps of reasoning to be analysed.
Outcome: The proposed dataset shows that existing language models exhibit weak performance on complex reasoning.

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