Papers by Hai Ye
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation (2021.acl-long)
Copied to clipboard
Ruidan He, Linlin Liu, Hai Ye, Qingyu Tan, Bosheng Ding, Liying Cheng, Jiawei Low, Lidong Bing, Luo Si
| Challenge: | Existing studies have shown that adapter-based tuning is more parameter-efficient than fine-tuning. |
| Approach: | They propose to add adapter modules to a pretrained language model and update the parameters of adapter module when learning on a downstream task. |
| Outcome: | The proposed method outperforms fine-tuning on low-resource and cross-lingual tasks and settings. |
On the Robustness of Question Rewriting Systems to Questions of Varying Hardness (2022.acl-long)
Copied to clipboard
| Challenge: | entailment : absence of questions classified based on their rewriting hardness or difficulty . enactment of QR system to rewrite context-dependent questions in CQA requires context knowledge . |
| Approach: | They propose a heuristic method to automatically classify questions into subsets of varying hardness . they then conduct a human evaluation to annotate the rewriting hardness of questions . |
| Outcome: | The proposed learning framework improves the overall performance compared to baselines. |
Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)
Copied to clipboard
Shulei Wang, Shuai Yang, Wang Lin, Zirun Guo, Sihang Cai, Hai Huang, Ye Wang, Jingyuan Chen, Tao Jin
| Challenge: | Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types. |
| Approach: | They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets. |
| Outcome: | The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning. |
Preference-Guided Reflective Sampling for Aligning Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Repeated random sampling is a widely used method that independently queries the model multiple times to generate outputs. |
| Approach: | They propose a more efficient method for iterative data generation and model re-training that leverages tree-based tree-derived generation framework to enable more efficient sampling. |
| Outcome: | The proposed method significantly outperforms repeated random sampling in best-of-N sampling on AlpacaEval and Arena-Hard. |
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment (2026.acl-long)
Copied to clipboard
Jiwei Tang, Zhicheng Zhang, Shunlong Wu, Jingheng Ye, Lichen Bai, Zitai Wang, Tingwei Lu, Lin Hai, Yiming Zhao, Hai-Tao Zheng, Hong-Gee Kim
| Challenge: | Large Language Models (LLMs) have achieved remarkable performance across NLP tasks . however, in long-context scenarios, they face high computational cost and information redundancy. |
| Approach: | They propose an encoder-decoder context compression framework that generates a compact sequence of soft tokens for downstream tasks. |
| Outcome: | Experiments show that GMSA outperforms baselines on multiple long-context question answering and summarization benchmarks while maintaining low end-to-end latency. |
Semi-Supervised Learning for Neural Keyphrase Generation (D18-1)
Copied to clipboard
| Challenge: | Existing models for keyphrase generation only use labeled data, which is limited to resource-rich domains. |
| Approach: | They propose semi-supervised keyphrase generation methods by leveraging labeled data and large-scale unlabeled samples for learning. |
| Outcome: | The proposed methods outperform state-of-the-art models trained with labeled data and large-scale unlabeled samples for learning. |
Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization (P19-1)
Copied to clipboard
| Challenge: | Semantic parsing aims to transform natural language utterances into formal meaning representations (MRs) whereas an NL generator achieves the reverse, the two tasks are often studied separately. |
| Approach: | They propose a method of dual information maximization to regularize the learning process by matching the joint distributions of p and q of NLs. |
| Outcome: | The proposed method empirically maximizes the variational lower bounds of expected joint distributions of NL and MRs. |
A DQN-based Approach to Finding Precise Evidences for Fact Verification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fact verification do not target the retrieval of precise evidences. |
| Approach: | They propose a DQN-based approach to retrieval of precise evidences . they propose best thresholds for determining the true labels of computed evidences. |
| Outcome: | The proposed method improves accuracy of fact verification by reducing label bias . it can retrieve evidence consisting of the first two sentences, but it can contain unnecessary sentences . |
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Recent research on test-time adaptation suggests a possible way to improve the generalization ability of LLMs. |
| Approach: | They propose to use multi-armed bandit learning and multi-arm dueling bandits to solve a multi-source test-time model adaptation problem from user feedback. |
| Outcome: | The proposed model is more effective than other strong baselines on extractive question answering datasets. |
Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have achieved great success in question answering, but their robustness is insufficient to support their practical applications. |
| Approach: | They propose a method which regularizes the model's output and an efficient side block to reduce its inference time. |
| Outcome: | The proposed method achieves comparable or better results than previous TTA methods at a speed close to vanilla forward propagation, which is 1.8 to 4.4 speedup compared to previous methods. |
Rationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing writing assistants rely on supervised fine-tuning to optimize models for multiple revisions. |
| Approach: | They propose a framework that enhances WA performance with rationale and alignment. |
| Outcome: | The proposed framework outperforms state-of-the-art WAs and the closed-source GPT-4o by 3.9 and 7.1 points on average across eight well-established writing-related test sets. |
Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing mPLMs can align representations well for myriads of cross-lingual transfer tasks. |
| Approach: | They propose enhanced isotropy and constrained code-switching for zero-shot cross-lingual transfer to alleviate the problem of misalignment caused by anisotropic representations. |
| Outcome: | The proposed method improves on three zero-shot cross-lingual transfer tasks and over existing methods. |
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models generate unintended outputs due to their unsupervised nature. |
| Approach: | They propose a method to construct preference pairs of selected and rejected LLMs by repeated random sampling to improve alignment performance. |
| Outcome: | The proposed method improves performance as the sample size increases. |
Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions (N18-1)
Copied to clipboard
| Challenge: | Existing work on court view generation from fact descriptions has improved the working efficiency of legal assistant systems. |
| Approach: | They propose to decode court views conditioned on encoded charge labels from the fact description in a criminal case to improve interpretability of charge prediction systems. |
| Outcome: | The proposed model can generate court views conditioned on encoded charge labels. |
Interpretable Rationale Augmented Charge Prediction System (C18-2)
Copied to clipboard
| Challenge: | Existing studies treat charge prediction as a text classification problem, but in the field of justice, every decision may be a matter of life and death. |
| Approach: | They propose to extract readable rationales from text and then create a rationale augmented classification model to enhance the prediction accuracy. |
| Outcome: | The proposed system can extract readable rationales in a high consistency with manual annotation and is comparable with the attention model in prediction accuracy. |
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Adapting pre-trained language models (PrLMs) to new domains has gained much attention . Adaptation of PrLMs to newdomains is important, but requires fine-tuning . |
| Approach: | They propose to use PrLMs to adapt to new domains without fine-tuning . they use class-aware feature self-distillation to learn discriminative features . |
| Outcome: | The proposed model can learn discriminative features from pre-trained language models without fine-tuning. |
Robust Question Answering against Distribution Shifts with Test-Time Adaption: An Empirical Study (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on robustness tuning (RT) methods has found that QA models fail when the test data has a distribution shift compared to the training data. |
| Approach: | They propose to use test-time adaptation methods to improve QA models after deployment to evaluate their model against text corruption and changes in language and domain. |
| Outcome: | The proposed method improves TTA to be more robust to variation in hyper-parameters and test distributions over time. |