Papers by Di Cao

11 papers
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models (2025.acl-demo)

Copied to clipboard

Challenge: Existing interpretation methods only support tasks with specific inputs, limiting their practical applications.
Approach: They propose an extensible module that matches different input data with interpretation methods and consolidates the interpreting outputs.
Outcome: The proposed module can match different input data with interpretation methods and consolidate the interpreting outputs.
D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Copied to clipboard

Challenge: Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach: They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome: The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .
BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics (2023.acl-long)

Copied to clipboard

Challenge: Existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, but they are insufficient for diagnosing whether metrics are consistent, effective on human-written texts, and sensitive to different error types.
Approach: They propose to use unfaithful minimal pairs to measure the consistency of automatic faithfulness metrics by comparing human-written summary pairs with a dataset of 889 human-writing, minimally different summary pairs.
Outcome: The proposed benchmarks show that the most discriminative metrics tend not to be the most consistent, and that the best performing metrics are sensitive to errors.
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training (2026.acl-long)

Copied to clipboard

Challenge: Existing threat models underestimate subset-training privacy risks because of the scale of modern datasets.
Approach: They propose a unified framework for analyzing privacy leakage in subset selection based on side-channel metadata from the subset process or via the outputs of the target model.
Outcome: The proposed framework analyzes privacy leakage in subset selection based on two different scenarios .
Binarized LSTM Language Model (N18-1)

Copied to clipboard

Challenge: Long short-term memory (LSTM) language models are widely used for automatic speech recognition and natural language processing (NLP) however, they are limited by the word embedding layer.
Approach: They propose to encode words into binary vectors and use binarized LSTM parameters to achieve high memory compression.
Outcome: The proposed model achieves 11.3 compression ratio without loss of performance and 31.6 compression ratio with acceptable performance degradation.
CODEMENV: Benchmarking Large Language Models on Code Migration (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored.
Approach: They propose a benchmark to evaluate large language models’ performance in handling code migration tasks.
Outcome: The proposed benchmark comprises 922 data points across 19 Python and Java packages and offers three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments.
Meta-Task Prompting Elicits Embeddings from Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for large language modeling are based on task-related instructions or prompts.
Approach: They propose a method for generating high-quality sentence embeddings from Large Language Models (LLMs) using meta-task prompts.
Outcome: The proposed method produces high-quality sentences without fine-tuning . it excels on STS benchmarks and in downstream tasks, surpassing models with similar prompts .
RealVul: Can We Detect Vulnerabilities in Web Applications with LLM? (2024.emnlp-main)

Copied to clipboard

Challenge: a lack of research specifically focused on vulnerabilities in the PHP language hinders the model’s ability to effectively capture the characteristics of specific vulnerabilities.
Approach: They propose a framework that can isolate potential vulnerability triggers while streamlining code and eliminating unnecessary semantic information.
Outcome: The proposed framework can isolate potential vulnerability triggers while streamlining the code and eliminating unnecessary semantic information.
Towards Multi-System Log Anomaly Detection (2025.acl-industry)

Copied to clipboard

Challenge: Existing models require dataset-specific training, causing costly procedures and performance bottlenecks.
Approach: They propose a log anomaly detection model with semantic relational reasoning that extracts cross-system semantic patterns and encodes them as high-dimensional learnable vectors.
Outcome: The proposed model extracts cross-system semantic patterns and encodes them as high-dimensional learnable vectors.
Multi-View Source Ablation for Faithful Summarization (2023.findings-eacl)

Copied to clipboard

Challenge: MuFaSSa is a metric for evaluating faithfulness of abstractive summaries . it uses different strategies to remove information from source document to form multiple ablated views .
Approach: They propose a metric for evaluating faithfulness of abstractive summaries using multiple ablated views.
Outcome: The proposed metric outperforms existing models on summarization tasks and human-annotated faithfulness labels.
CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation (2025.acl-industry)

Copied to clipboard

Challenge: CodeIF assesses the ability of large language models to adhere to task-oriented instructions in code generation tasks.
Approach: They introduce a benchmark designed to assess LLMs' ability to adhere to task-oriented instructions within diverse code generation scenarios.
Outcome: The proposed benchmark assesses LLMs' ability to adhere to task-oriented instructions in code generation tasks across a wide range of complexity levels and programming domains.

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