Papers by Haipeng Zhang
Analyze Like a Venture Capitalist: Information-Gain and Knowledge Enhanced Graph Reasoning for Startup Success Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Most venture capital investments fail, while a few deliver outsized returns. |
| Approach: | They propose a framework that synthesizes relational evidence across sources . they propose combining information-gain-driven retriever and knowledge base to ground reasoning . |
| Outcome: | The proposed framework achieves +5.9% F1 and +22.1% Precision@5 over state-of-the-art baselines. |
Confidence-Aware Ranker Ensembles for Robust In-Context Knowledge Editing (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel at factual recall, but can propagate stale or incorrect knowledge. |
| Approach: | They propose a feature-weighted ensemble for in-context knowledge editing that calibrates three heterogeneous rankers and extracts simple confidence features from each ranker. |
| Outcome: | The proposed method achieves 88.33% Edit-Success Rate over the best single retriever . it improves edit accuracy without touching model weights and approaches oracle upper bound (91%). |
Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks (2025.acl-long)
Copied to clipboard
| Challenge: | Existing models excel in arithmetic reasoning but their generalization capabilities are incompletely understood. |
| Approach: | They propose a theoretical framework for understanding the generalization behaviors of transformers in arithmetic tasks, focusing on length generalization. |
| Outcome: | The proposed framework can predict generalization behaviors in transformers with a high translation invariance and base mismatch in modular operations. |
FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reranking frameworks optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents. |
| Approach: | They propose a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema. |
| Outcome: | FINCARDS improves early-rank retrieval over lexical and LLM-based reranking baselines while reducing ranking variance. |
Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models excel at factual recall yet propagate stale or incorrect knowledge. |
| Approach: | They propose a framework that allows users to rank demonstrations by editing reward . it uses a *learnable threshold* to prune low-value examples, reducing edit success by 17.1% . |
| Outcome: | The proposed framework improves edit success by 17.1% and reduces latency by 41.6% on the CounterFact benchmark. |
ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text classification use only encoders or decoders that do not allow for the use of labels in unseen domains. |
| Approach: | They propose an autoencoder that encodes text into two disentangled spaces and decodes it to generate text with labels in the unseen domains. |
| Outcome: | The proposed model outperforms the existing methods in label-partially-unseen and label-fully-un-seeen scenarios and even outperfects the SOTA methods. |
MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking (2023.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that MoNET outperforms previous DST methods in alleviating state momentum issues and improving the anti-noise ability. |
| Approach: | They propose to use previous state of each turn in training data as input to learn to predict current state. |
| Outcome: | The proposed model outperforms existing methods on multiWOZ datasets and shows that it can update and correct slot values and improve anti-noise ability. |
CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing few-shot dialogue state tracking (DST) methods transfer knowledge from labeled data into DST, but collecting large amount of labeles is laborious. |
| Approach: | They propose a few-shot dialogue state tracking framework that integrates self-training and self-supervised learning methods into the framework. |
| Outcome: | The proposed framework achieves competitive performance in several few-shot scenarios. |