Papers by Siyue Zhang

10 papers
A Survey of Reasoning-Intensive Retrieval: Progress and Challenges (2026.acl-long)

Copied to clipboard

Challenge: Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting evidence, rather than semantic similarity.
Approach: They propose a taxonomy that categorizes methods based on where and how reasoning is integrated into the retrieval pipeline.
Outcome: The proposed method framework provides a detailed analysis of the current landscape and its trade-offs and practical applications.
Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing (2026.acl-long)

Copied to clipboard

Challenge: Composed Image Retrieval (CIR) is a complex task in multimodal understanding . current CIR benchmarks lack a robust evaluation pipeline and limited query categories .
Approach: They construct a fine-grained CIR benchmark that allows for precise control over modification types and content.
Outcome: The proposed benchmark covers 5,000 high-quality queries structured across five main categories and fifteen subcategories.
RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Long-tail question answering presents significant challenges for large language models due to limited ability to acquire and accurately recall less common knowledge.
Approach: They propose a data augmentation framework that selects high-quality easy-to-learn training data to enhance dense retrieval models.
Outcome: The proposed framework improves on two long-tail retrieval benchmarks, PopQA and EntityQuestion, and shows that it outperforms existing retrievers on extremely long-tailed questions.
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective (2025.emnlp-main)

Copied to clipboard

Challenge: Large language model (LLM)-based embedding models surpass BERT and T5 on general-purpose text embeddable tasks.
Approach: They propose to adopt diffusion language models for text embeddings to overcome limitations in unidirectional attention used during autoregressive pre-training.
Outcome: The proposed model outperforms the existing LLM-based embedding model on reasoning tasks by 20% and 2% on traditional embeddable benchmarks.
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation benchmarks for retrievers are narrow and evaluate them in isolation . existing evaluation benchmarking frameworks focus on evaluating retrievers in isolation, obscuring their value in real-world applications.
Approach: They propose an evaluation framework that evaluates retrievers in agentic search systems . they provide expert-annotated reasoning aspects, positive documents, a reference response and evaluation rubrics .
Outcome: The proposed framework assesses retrievers in agentic search systems.
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA (2024.findings-emnlp)

Copied to clipboard

Challenge: Text-to-SQL parsing and end-to end question answering have yet to be compared and their synergy remains unexplored.
Approach: They propose a Synergistic Table-based Question Answering approach that integrates different models via answer selection.
Outcome: The proposed approach improves on multiple benchmarks and on large scale datasets.
LimRank: Less is More for Reasoning-Intensive Information Reranking (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to rerank information require large-scale fine-tuning, which is computationally expensive.
Approach: They propose an open-source pipeline for generating diverse, challenging, and realistic reranking examples.
Outcome: The proposed model performs competitively on two benchmarks, while being trained on less than 5% of the data typically used in prior work.
MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for answering time-sensitive questions lack temporal reasoning . existing methods struggle with these time-intensive questions, authors say .
Approach: They propose a temporal-based question-answering framework that integrates temporal perturbations and gold evidence labels into a question processing framework.
Outcome: The proposed framework outperforms baseline retrieval methods in retrieval performance.
MCC-KD: Multi-CoT Consistent Knowledge Distillation (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable abilities in complex reasoning through chain of thought (CoT) prompting.
Approach: They propose to generate multiple rationales for each question and enforce consistency among their predictions by minimizing the bidirectional KL-divergence between the answer distributions.
Outcome: The proposed model achieves superior performance on in-distribution and commonsense reasoning benchmarks.
SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for retrieval-augmented reasoning on numerical sports questions focus on one or two evidence units.
Approach: They propose a benchmark for retrieval-augmented reasoning on numerical sports questions . they evaluate existing retrievers and rerankers, along with agentic Retrieval-Augmented Generation systems.
Outcome: The proposed benchmarks focus on the sports domain because it offers rich multi-modal resources.

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