Papers by Jianfei Zhang

9 papers
Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching (2025.findings-acl)

Copied to clipboard

Challenge: In-Context Learning (ICL) empowers Large Language Models for rapid task adaptation without fine-tuning.
Approach: They propose a method that aligns fine-tuning gradients between entire training set and selected examples to enable in-context learning and fine-uning.
Outcome: The proposed method outperforms random selection on large LLMs from 4-shot to 128-shot scenarios across 9 datasets.
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining (2026.acl-long)

Copied to clipboard

Challenge: Existing research suggests that multilingual large language models can achieve impressive cross-lingual understanding despite largely monolingual pretraining.
Approach: They compare a monolingual-only corpus with a standard web corpus that removes all multilingual documents and then retrain the models from scratch under controlled conditions.
Outcome: The results show that removing bilingual data causes translation performance to drop 56% in BLEU, whereas code-switching contributes minimally.
Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)

Copied to clipboard

Challenge: Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China.
Approach: They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform.
Outcome: The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower.
Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment (2025.coling-main)

Copied to clipboard

Challenge: Human values are inherently diverse, making it insufficient to align LLMs solely with general preferences.
Approach: They propose a flexible paradigm for individual preference alignment that disentangles preference representation from text generation in LLMs.
Outcome: The proposed method produces aligned quality and better than PEFT-based methods while reducing training time for each new individual preference by 80% to 90%.
Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow (2025.findings-emnlp)

Copied to clipboard

Challenge: Decode-Only models propagate information from left to right, but the model's attention still focuses on the visual representations, resulting in hallucinations.
Approach: They propose to leverage the core information embedded in semantic representations to enhance the model's visual understanding by leveraging the attention distributions.
Outcome: The proposed method reduces hallucinations by 80% by aligning the attention distribution with the actual information flow.
PhonoThink: Improving Large Language Models’ Reasoning on Chinese Phonological Ambiguities (2025.emnlp-main)

Copied to clipboard

Challenge: Effectively resolving phonological ambiguities is crucial for robust natural language processing, as these ambiguity are pervasive in tasks ranging from speech-to-text, spelling correction, to offensive language detection.
Approach: They propose a framework to enhance LLMs’ phonological capability through a multiple-stage training approach.
Outcome: The proposed framework enables the base model to achieve comparable performance to a much larger model.
Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for text ranking are based on intuition, but their estimated transferability may not align well with the objectives of text ranking.
Approach: They propose to compute expected rank as transferability, explicitly reflecting the model’s ranking capability.
Outcome: The proposed method shows significant improvements over previous classification-oriented TE methods, human intuition, and ChatGPT with minor time consumption.
ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to code question answering use bi-modal and unimodal pretraining to align text and code representations.
Approach: They propose a modality-agnostic contrastive pre-training approach to improve alignment of text and code representations of current code language models.
Outcome: The proposed model exhibits significant performance improvements across a wide range of code retrieval benchmarks.
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to solve question answering (QA) problems are limited by the need for text generation and answer retrieval.
Approach: They propose to introduce QA interaction features in scoring function but at the cost of low efficiency in inference stage.
Outcome: The proposed framework significantly outperforms the state-of-the-art method on multiple answer retrieval datasets.

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