63 citations · 82 across the 16 of their papers we have counts for
20 papers
KEEP-Bench: Evaluating Evidence Preservation in Context Compression
Ziqing Man, Di Wu, Jia-Chen Gu +3
Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader…
Lean Graph Search for Formal Theorem Proving
Yihan Xu, Jia-Chen Gu, Junyi Zhang +7
Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems…
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
Di Wu, Zixiang Ji, Asmi Kawatkar +4
Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure m…
Open-Domain Safety Policy Construction
Di Wu, Siyue Liu, Zixiang Ji +4
Moderation layers are increasingly a core component of many products built on user- or model-generated content. However, drafting and maintaining domain-specific safety policies re…
BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
Jia-Chen Gu, Junyi Zhang, Di Wu +3
As retrieval-augmented generation (RAG) tackles complex tasks, increasingly expanded contexts offer richer information, but at the cost of higher latency and increased cognitive lo…
VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
Di Wu, Yixin Wan, Kai-Wei Chang
Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such…
Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
Di Wu, Jia-Chen Gu, Kai-Wei Chang +1
Selective retrieval aims to make retrieval-augmented generation (RAG) more efficient and reliable by skipping retrieval when an LLM's parametric knowledge suffices. Despite promisi…
BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression
Yuankai Li, Jia-Chen Gu, Di Wu +2
Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the inp…
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
Di Wu, Hongwei Wang, Wenhao Yu +3
Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized re…
The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention
Yixin Wan, Di Wu, Haoran Wang +1
Prompt-based "diversity interventions" are commonly adopted to improve the diversity of Text-to-Image (T2I) models depicting individuals with various racial or gender traits. Howev…
MetaKP: On-Demand Keyphrase Generation
Di Wu, Xiaoxian Shen, Kai-Wei Chang
Traditional keyphrase prediction methods predict a single set of keyphrases per document, failing to cater to the diverse needs of users and downstream applications. To bridge the…
Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation
Di Wu, Jia-Chen Gu, Fan Yin +2
Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. However, there are significant trustworthiness concer…
Repoformer: Selective Retrieval for Repository-Level Code Completion
Di Wu, Wasi Uddin Ahmad, Dejiao Zhang +2
Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. However, the invariable use of retrieval in existing methods e…
On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation
Di Wu, Wasi Uddin Ahmad, Kai-Wei Chang
This study addresses the application of encoder-only Pre-trained Language Models (PLMs) in keyphrase generation (KPG) amidst the broader availability of domain-tailored encoder-onl…
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Po-Nien Kung, Fan Yin, Di Wu +2
Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. Howeve…
Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models
Di Wu, Wasi Uddin Ahmad, Kai-Wei Chang
Keyphrase Generation (KPG) is a longstanding task in NLP with widespread applications. The advent of sequence-to-sequence (seq2seq) pre-trained language models (PLMs) has ushered i…
Virtual histological staining of unlabeled autopsy tissue
Yuzhu Li, Nir Pillar, Jingxi Li +12
Histological examination is a crucial step in an autopsy; however, the traditional histochemical staining of post-mortem samples faces multiple challenges, including the inferior s…
KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
Di Wu, Da Yin, Kai-Wei Chang
Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human re…
Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study
Di Wu, Wasi Uddin Ahmad, Kai-Wei Chang
Neural models that do not rely on pre-training have excelled in the keyphrase generation task with large annotated datasets. Meanwhile, new approaches have incorporated pre-trained…
Representation Learning for Resource-Constrained Keyphrase Generation
Di Wu, Wasi Uddin Ahmad, Sunipa Dev +1
State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data. To overcome this chal…