Papers by Quanyu Long
Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance? (2025.naacl-long)
Copied to clipboard
| Challenge: | Fact-checking pipelines adopt the Decompose-Then-Verify paradigm, where texts are broken down into smaller claims for individual verification and subsequently combined for a veracity decision. |
| Approach: | They propose to categorize decomposition errors and to reveal a trade-off between accuracy gains and noise introduced by decomposing. |
| Outcome: | The proposed analysis provides new insights into understanding current system’s instability and offers guidance for future studies toward improving claim decomposition in fact-checking pipelines. |
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts (2025.acl-long)
Copied to clipboard
Ziwei Huang, Wanggui He, Quanyu Long, Yandi Wang, Haoyuan Li, Zhelun Yu, Fangxun Shu, Weilong Dai, Hao Jiang, Fei Wu, Leilei Gan
| Challenge: | Existing studies on text-to-image (T2I) models focus on text alignment, image quality, and object composition capabilities. |
| Approach: | They propose a T2I-FactualBench benchmark to evaluate the factuality of knowledge-intensive concept generation. |
| Outcome: | The proposed framework evaluates the factuality of knowledge-intensive concept generation tasks. |
On the Robustness of Language Encoders against Grammatical Errors (2020.acl-main)
Copied to clipboard
| Challenge: | Pre-trained language encoders are effective in facilitating downstream natural language processing tasks, but they often assume training and test corpora are clean and it is unclear how the models behave when confronted with noisy input. |
| Approach: | They conduct adversarial attacks to simulate grammatical errors on clean text data. |
| Outcome: | The proposed model performs better when confronted with natural grammatical errors than when faced with noisy input. |
Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks. |
| Approach: | They propose a tri-encoder sequential retriever that models a Markov Decision Process (MDP) this method decomposes the probability of retrieving a set of elements into a sequence of conditional probabilities and allows each retrieval step to be conditioned on previously selected examples. |
| Outcome: | The proposed method outperforms baselines and shows that it can handle multiple pieces of evidence or examples. |
Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to compress video inputs ignore the importance of static and dynamic information in long videos, leading to inefficient token usage within limited budgets. |
| Approach: | They propose a token selection strategy that adaptively adjusts static and dynamic information based on question requirements. |
| Outcome: | The proposed method achieves performance improvements (up to 5.8%) on multiple video question answering benchmarks. |
Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multi-hop claim verification require multi-step reasoning to construct verification chains while iterating for information to uncover hidden bridging facts. |
| Approach: | They propose a hierarchical agent reasoning and information search model that integrates reasoning and search-informed reasoning. |
| Outcome: | Experimental results show that HARIS improves multi-hop claim verification accuracy and interpretability. |
Domain Confused Contrastive Learning for Unsupervised Domain Adaptation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing studies on domain-shifting adaptations have focused on domain . |
| Approach: | They propose a self-supervised approach to unsupervised domain adduction using domain puzzles to bridge the source and target domains and retain discriminative representations after adaptation. |
| Outcome: | The proposed approach outperforms baselines and further ablation studies show that it is more stable and effective when performing other data augmentations. |
From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation (2026.acl-long)
Copied to clipboard
| Challenge: | a naive application of GRPO leads to conflicting gradient signals and a misalignment with the temporal dynamics of the diffusion process. |
| Approach: | They propose a framework that uses synergy-aware reward shaping to penalize conflicted reward signals and amplify synergies to provide a sharper and decisive gradient. |
| Outcome: | The proposed framework outperforms naive GRPO and Time-Aware Dynamic Weighting (TDW) on DreamBench, and achieves a state-of-the-art balance between ID preservation and prompt adherence. |
Programming over Thinking: Efficient and Robust Multi-Constraint Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing large language model approaches lack flexibility in multi-constraint planning . SCOPE achieves state-of-the-art performance while lowering cost and latency . |
| Approach: | They propose a framework that disentangles query-specific problem reasoning from generic code execution. |
| Outcome: | The Scalable Code Planning Engine achieves state-of-the-art performance while lowering cost and latency. |
Generative Imagination Elevates Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing multimodal neural machine translation methods require triplets of bilingual sentence - image for training and tuples of source sentence . Existing methods require truncated images for inference, but ImagiT uses both source sentence and “imagined representation” to produce a target translation. |
| Approach: | They propose a multimodal machine translation method using visual imagination to generate a target translation from a sentence in a source language. |
| Outcome: | The proposed method significantly outperforms the existing text-only neural machine translation baselines and improves translation quality. |
Adapt in Contexts: Retrieval-Augmented Domain Adaptation via In-Context Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have demonstrated their capability with few-shot inference . however, in-domain demonstrations are not always available in real scenarios . |
| Approach: | They propose unsupervised domain adaptation problem to adapt language models from source domain to target domain without any target labels. |
| Outcome: | The proposed model performs better than baseline models on Sentiment Analysis and Named Entity Recognition tasks. |