Papers by Yunfei Lu

12 papers
Ciron: a New Benchmark Dataset for Chinese Irony Detection (2020.lrec-1)

Copied to clipboard

Challenge: Automatic Chinese irony detection often lacks labeled benchmark datasets . despite its pervasive nature, irony is a trope whose actual meaning differs from what is literally enunciated.
Approach: They propose to use a Chinese benchmark dataset for automatic Chinese irony detection to provide a benchmark for machine learning models.
Outcome: The proposed dataset includes more than 8.7K posts, collected from Weibo, a micro blogging platform.
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach: They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome: The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to enhance multilingual reasoning capabilities rely on costly multilingual training or employ prompting with external translation tools.
Approach: They propose a training-free inference-time method to enhance multilingual reasoning capabilities via Representation Engineering without additional training data or tools.
Outcome: The proposed method outperforms existing methods on four reasoning benchmarks in English and Thai and Swahili.
CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination.
Approach: They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns.
Outcome: The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages.
Specialization without Sparsity: Efficient and Expressive Split-Path Experts for LLM Fine-Tuning (2026.findings-acl)

Copied to clipboard

Challenge: Parameter-efficient fine-tuning (PEFT) is a low-cost alternative to full fine-timing due to the massive overhead.
Approach: They propose a Mixture-of-Experts approach that enhances specialization while maintaining low resource overhead.
Outcome: The proposed approach outperforms or matches state-of-the-art methods on GLUE, GSM8K, MBPP, and a text rewriting task from SmolTalk.
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)

Copied to clipboard

Challenge: Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge .
Approach: They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST .
Outcome: The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance .
Affection Driven Neural Networks for Sentiment Analysis (2020.lrec-1)

Copied to clipboard

Challenge: Existing deep neural network models lack mechanisms to highlight important sentiment terms.
Approach: They propose a method to incorporate affective knowledge into deep neural network models by mapping affective influence vectors to an affective impact value and integrating them into long-term memory models to highlight affective terms.
Outcome: The proposed approach improves on three large datasets by 1.0% to 1.5% on the benchmark datasets.
Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on large language models focus on literal-level translation quality, such as adequacy and fluency.
Approach: They propose a Culture-Aware Novel-Driven Parallel Dataset for Machine Translation and a multi-dimensional evaluation framework for assessing cultural translation quality.
Outcome: The proposed model improves evaluation reliability in LLM-as-a-judge scenarios under culture-aware constraints.
x1: Learning to Think Adaptively Across Languages and Cultures (2026.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs) ignore this diversity by reasoning in a single dominant language.
Approach: They propose a family of reasoning models that can adaptively reason in an advantageous language on a per-instance basis.
Outcome: The proposed model can reason in a single dominant language on a per-instance basis.
MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms? (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, the top-performing models achieve a 48.8% task completion rate on realizing machine learning algorithms .
Approach: They propose a benchmark to test machine learning's ability to generate ML code for humans . they propose an automatic evaluation framework with metrics such as task pass rate and time overhead .
Outcome: The proposed benchmark is unique in its focus on interpreting complex human instructions and producing multi-step, high-complexity code.
CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning (2025.acl-long)

Copied to clipboard

Challenge: Existing fine-tuning approaches that focus on English-centric training corpora often introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-linguistic interactions.
Approach: They propose a multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level.
Outcome: The proposed model outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods.
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing GUI benchmarks lack fine-grained diagnostics to identify which capabilities lead to task failures.
Approach: They propose a multilingual P R GUI Benchmark to assess LVLMs' language capabilities . they propose XLI to align non-English hidden states with English ones during inference .
Outcome: The proposed benchmark reveals consistent gaps between English and non-English settings . it reduces the cross-lingual gaps with an average gain of 6.5% in non- English settings compared to static benchmarks .

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