Papers by Hongfu Liu

6 papers
Unlocking Large Audio-Language Models for Interactive Language Learning (2026.findings-eacl)

Copied to clipboard

Challenge: Computer-Assisted Pronunciation Training (CAPT) systems provide unintuitive feedback that lacks actionable guidance.
Approach: They propose to use audio-language models to provide more user-friendly feedback for pronunciation training.
Outcome: The proposed model outperforms baselines on mispronunciation detection and suggestion generation.
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent efforts have identified adversarial suffixes capable of jailbreaking LLMs . however, GCG struggles with computational inefficiency, limiting further studies .
Approach: They propose a two-stage transfer learning framework which decouples the search process into behavior-agnostic pre-searching and behavior-relevant post-search.
Outcome: The proposed approach outperforms baseline on Llama2-chat-7b with ASRs of 43.9 (+ 22.2) and 39.0 (+ 19.5) on valid and test sets.
Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations (2024.acl-long)

Copied to clipboard

Challenge: Discursive Socratic Questioning (DISQ) assesses a model's understanding of discourse relations by requiring systematic accuracy over multiple questions.
Approach: They propose a method that evaluates faithfulness of understanding discourse based on question answering.
Outcome: The proposed method evaluates the faithfulness of understanding discourse based on question answering.
Advancing Test-Time Adaptation in Wild Acoustic Test Settings (2024.emnlp-main)

Copied to clipboard

Challenge: Existing wild vision TTA methods fail to handle speech data due to the unique characteristics of high-entropy speech frames, which are unreliably filtered out even when containing crucial semantic content.
Approach: They propose a method for acoustic foundation models to perform confidence-based adaptation in wild acustic test settings.
Outcome: The proposed method outperforms baselines under Gaussian noise, environmental sounds, accent variations, and sung speech in the wild.
Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language models (LLMs) have the capability to engage In-context Learning (ICL) however, this particular learning paradigm suffers from high instability stemming from factors such as input distribution, order and prompt formats.
Approach: They propose to quantify the information gain obtained in prediction after observing a given example candidate and to sample those with maximum IG.
Outcome: The proposed method can yield an average relative improvement of 14.3% across six classification tasks using three LLMs.
Benchmarking Large Language Models on Communicative Medical Coaching: A Dataset and a Novel System (2024.findings-acl)

Copied to clipboard

Challenge: Existing applications of natural language processing (NLP) focus on patient-centered services, but the potential of NLP to benefit inexperienced doctors remains unexplored.
Approach: They propose a human-AI cooperative framework to assist medical learners in practicing communication skills during patient consultations.
Outcome: The proposed framework enables medical learners to practice communication skills during patient consultations while a coach agent provides immediate, structured feedback.

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