Papers by Xinran Zhao

16 papers
MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers (2025.emnlp-main)

Copied to clipboard

Challenge: Different retrievers offer distinct, often complementary signals, but they are not optimal for all queries.
Approach: They propose a zero-shot, weighted combination of heterogeneous retrievers . they validate this intuition by incorporating specialized non-oracle human information sources .
Outcome: Experiments show that a mixture of heterogeneous retrievers outperforms each retriever and larger models by +10.8% and +3.9% on average.
Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies on the confidence calibration of LLMs have not explored the effects of different prompting strategies on LLM performance.
Approach: They propose Fact-and-Reflection prompting which improves LLM confidence calibration . they propose to use human cognition to elicit known "facts" and ask model to "reflect" over them .
Outcome: The proposed method lowers the expected calibration error by 23.5% on multi-purpose QA tasks.
GeoHard: Towards Measuring Class-wise Hardness through Modelling Class Semantics (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances in measuring hardness-wise properties of data guide language models in sample selection within low-resource scenarios.
Approach: They propose to use class-wise hardness to measure class-specific properties of data in the semantic embedding space by modeling class geometry in the . semantic embeddining space.
Outcome: The proposed method surpasses instance-level metrics by over 59 percent on Pearson‘s correlation on measuring class-wise hardness.
Weakly Supervised Text Classification using Supervision Signals from a Language Model (2022.findings-naacl)

Copied to clipboard

Challenge: Existing weakly supervised text classification methods require a large number of annotated data and human annotations are expensive.
Approach: They propose to query a masked language model with cloze style prompts to obtain supervision signals.
Outcome: The proposed method outperforms baseline methods on three datasets by 2%, 4%, and 3%.
Towards Reference-free Text Simplification Evaluation with a BERT Siamese Network Architecture (2023.findings-acl)

Copied to clipboard

Challenge: Text simplification (TS) aims to modify sentences to make their content and structure easier to understand.
Approach: They propose a neural-network-based TS metric that uses a human reference to evaluate simplification and meaning preservation.
Outcome: The proposed metric correlates better with human judgments for simplicity and meaning preservation than existing metrics.
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach: They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome: The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020.acl-main)

Copied to clipboard

Challenge: a new task is developed to categorize essential commonsense knowledge for the Winograd Schema Challenge . a previous work focused on the classification of commonsensical knowledge by pre-trained models .
Approach: They propose a task that categorizes essential commonsense knowledge for the Winograd Schema Challenge . they leverage the collected reasons to identify plausible reasons from wrong ones .
Outcome: The proposed task aims to shed light on commonsense knowledge needed for better reasoning . it is based on the collected reasons and a new task called WinoWhy .
On Measuring the Intrinsic Few-Shot Hardness of Datasets (2022.emnlp-main)

Copied to clipboard

Challenge: Recent work has shown that few-shot learning is successful for pre-trained models, but there is no concrete understanding of when and why it is successful.
Approach: They propose a simple metric that estimates few-shot hardness for a given dataset . they propose metric which exploits feature-space invariances between training and test samples .
Outcome: The proposed metric better accounts for few-shot hardness compared to existing notions and is 8-100x faster to compute.
Probing Toxic Content in Large Pre-Trained Language Models (2021.acl-long)

Copied to clipboard

Challenge: Existing studies on pre-trained language models have shown that they carry harmful biases towards different social groups.
Approach: They propose a method to probe English, French, and Arabic PTLMs and quantify the potentially harmful content they convey with respect to a set of templates.
Outcome: The proposed method analyzes PTLMs to predict masked tokens at the end of sentences to assess their toxicity.
Leveraging Topic Relatedness for Argument Persuasion (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies of argumentation focus on the effects of factors such as source, audience, and language style, but the impact of exploiting the relationships among controversial topics is under-explored.
Approach: They propose to model topic relatedness among controversial topics using topic embedding features and topic semantics features extracted from the arguments.
Outcome: The proposed method improves predicting persuasiveness and generalizes to rare topics in a few-shot setting.
MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies show the importance of document retrieval in the scientific domain.
Approach: They propose a zero-shot approach to measure query-document similarity using atomic components in queries and documents to combine them into a united score.
Outcome: The proposed approach outperforms previous document retrieval methods by 24.7%, 9.8%, and 6.9% on nDCG@5 with unsupervised, supervised, and LLM-based retrievers.
SPHERE: An Evaluation Card for Human-AI Systems (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods and standards for human-AI systems are unclear, especially for large language models.
Approach: They propose an evaluation card SPHERE which provides a template for evaluation protocols . they outline current evaluation practices and areas for improvement .
Outcome: The evaluation card provides a template for designing evaluation protocols . it outlines current evaluation practices and areas for improvement .
On the Representation Geometry of LoRA Model Merging (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for low-rank Adaptation (LoRA) fine-tuning focus on globally shared structure . combining SVD with CUR improves performance of LoRA model merging .
Approach: They propose a training-free method that combines SVD and CUR decomposition to improve LoRA merging performance.
Outcome: The proposed procedure improves on vision and language benchmarks.
PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English (2022.lrec-1)

Copied to clipboard

Challenge: Existing PCR systems are not reliable in real applications due to weak semantic meanings of pronouns.
Approach: They propose a benchmark and toolbox that evaluates performance of PCR systems from different perspectives.
Outcome: The proposed benchmark and toolbox evaluates the performance of PCR systems from different perspectives.
Dense X Retrieval: What Retrieval Granularity Should We Use? (2024.emnlp-main)

Copied to clipboard

Challenge: a learned dense retrieval model is often overlooked when using a corpus for inference, resulting in a design choice of retrieval unit . granularity of retrievals is important for both retrieval and downstream tasks .
Approach: They propose a retrieval unit for dense retrieval that uses propositions to index corpus . propositions are defined as atomic expressions within text, each encapsulating a distinct factoid .
Outcome: The proposed retrieval unit outperforms passage-level units on retrieval and downstream tasks.
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code.
Approach: They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages .
Outcome: The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation.

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