Papers by Huajian Zhang

7 papers
Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks (2024.eacl-long)

Copied to clipboard

Challenge: Existing approaches to evaluate summary faithfulness are sub-optimal due to the granularity level considered for premises and hypotheses.
Approach: They propose a novel approach that uses a variable premise size and simplifies summary sentences into shorter hypotheses.
Outcome: The proposed model performs better on diverse summarisation tasks than existing models.
Lost in Literalism: How Supervised Training Shapes Translationese in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Large language models exhibit translationese errors and generate unexpected unnatural translations . Neural machine translation (NMT) has become the dominant method in machine translation research .
Approach: They evaluate the prevalence of translationese in LLM-generated translations and investigate its roots during supervised fine-tuning.
Outcome: The proposed methods reduce translationese while improving translation naturalness . the proposed methods are validated by human evaluations and automatic metrics .
Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Existing multimodal benchmarks often overlook counterfactual reasoning, which is crucial for robust video understanding.
Approach: They propose a multidimensional multimodal benchmark that systematically evaluates MLLMs across the abstract-concrete and perception-cognition dimensions.
Outcome: The proposed model decomposes complex queries into structured sub-questions, enabling fine-grained reasoning analysis.
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a problem of data contamination is now almost inevitable during the development of large language models, with the training data often integrating evaluation benchmarks even unintentionally.
Approach: They propose a framework to restore model performance prior to data contamination on potentially leaked datasets by using contamination detection and disruption operation.
Outcome: The proposed framework restores model performance prior to contamination on potentially leaked datasets.
What Have We Achieved on Non-autoregressive Translation? (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies have shown that non-autoregressive (NAT) methods underperform autoregressive methods (AT) however, their evaluation using BLEU has been shown to weakly correlate with human annotations.
Approach: They propose to evaluate four representative NAT methods using BLEU to narrow the performance gap between autoregressive and autoregressive translations.
Outcome: The proposed methods underperform NAT and autoregressive methods under more reliable evaluation metrics.
Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation (2023.acl-long)

Copied to clipboard

Challenge: Existing work on cross-lingual summarization (CLS) does not consider crosslingual sources for summarizing.
Approach: They propose a cross-lingual conversation summarization benchmark that explicitly considers source context.
Outcome: The proposed method surpasses baselines on ConvSumX and 3 widely-used manual annotations.
Leveraging Entailment Judgements in Cross-Lingual Summarisation (2024.findings-acl)

Copied to clipboard

Challenge: Synthetically created cross-lingual summarisation datasets are prone to include document-summary pairs where the reference summary is unfaithful to the corresponding document.
Approach: They propose to use off-the-shelf cross-lingual Natural Language Inference to evaluate faithfulness of reference and model generated summaries and use unlikelihood loss to teach a model about unfaithful summary sequences.
Outcome: The proposed approach evaluates faithfulness of reference and model generated summaries and uses unlikelihood loss to teach a model about unfaithful summary sequences.

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