Papers by Shudong Liu

8 papers
From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG (2026.findings-acl)

Copied to clipboard

Challenge: Existing multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities, making failures unverifiable.
Approach: They propose a multimodal benchmark that features real-world landmarks with annotations across multiple viewpoints and a framework that treats visual elements as first-class retrieval units through three stages: element-level detection and classification, multi-granularity cross-modal alignment for evidence retrieval, and attribution-constrained generation.
Outcome: The proposed framework achieves up to 29.2% improvement over six strong baselines for this task.
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches lack robustness to handle complex edge cases and generalizability across different domains.
Approach: They develop an accurate and lightweight verifier model for evaluation and outcome reward that matches unstructured outputs against standard answers.
Outcome: The proposed model can process multiple answer types including multi-subproblems, formulas, and sequence answers while identifying abnormal/invalid responses.
Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit excessive, random, and uninformative uncertainty rendering them unsuitable for decision-making in human-computer interactions.
Approach: They propose an uncertainty-aware instruction tuning method that aligns LLMs’ perception with the probabilistic uncertainty of the generation.
Outcome: The proposed method improves LLMs' performance by 45.2%, with reasonably good out-of-domain generalization capabilities.
Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to transfer knowledge from kNN datastore into new models are expensive and arbitrarily transfer knowledge.
Approach: They propose a domain-aware method which filters out domain-relevant neighborhood knowledge for learning in the distillation process.
Outcome: The proposed method achieves state-of-the-art on four domain translation tasks.
Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing summarization benchmarks overlap in time with pre-training corpora and fine-tuning datasets.
Approach: They propose a temporal generalization benchmark that contains data samples from 2010 to 2022 to understand the temporal ability of abstractive summarization models.
Outcome: The proposed benchmark analyzes data samples from 2010 to 2022 to understand the temporal generalization ability of abstractive summarization models.
TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks (2024.naacl-long)

Copied to clipboard

Challenge: Information extraction (IE) tasks have a variety of schemas and objectives that differ across tasks.
Approach: They propose a paradigm where all IE tasks are aligned to learn the same goals . they use two universal relations to extract mention spans and type recognition .
Outcome: The proposed model achieves state-of-the-art on established benchmarks spanning 16 datasets, spanning 7 diverse IE tasks.
kNN-TL: k-Nearest-Neighbor Transfer Learning for Low-Resource Neural Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: Transfer learning is an effective technique for enhancing low-resource neural machine translation (NMT) however, these methods do not make use of the parent knowledge during the child inference, which may limit the translation performance.
Approach: They propose a k-Nearest-Neighbor Transfer Learning approach which leverages the parent knowledge throughout the entire developing process of the child model.
Outcome: The proposed approach outperforms strong baselines on four low-resource translation tasks.
Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their capability in visual procedure question answering (VP-QA) remains largely unexplored.
Approach: They propose a multimodal benchmark specifically designed for visual procedural reasoning that synergizes cross-modal procedure retrieval, context-aware step decomposition, and the next step prediction.
Outcome: The proposed framework significantly outperforms baselines on visual procedure question answering (VP-QA) Experiments on six VLMs show that it performs better than baselines.

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