Papers by Jiawei Zhao

18 papers
Non-Linearity in Mapping Based Cross-Lingual Word Embeddings (2020.lrec-1)

Copied to clipboard

Challenge: Existing work on cross-lingual word embeddings rely on linear mappings, but this assumption is not true for all language pairs.
Approach: They propose a non-linear mapping approach which can find non-linesar relationships between languages by kernel Canonical Correlation Analysis.
Outcome: The proposed approach improves on five language pairs on supervised and self-learning scenarios.
CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus.
Approach: They propose a power-law relationship between loss, mixture ratio, and training tokens scale and formalize the trade-off between general and domain-specific capabilities.
Outcome: The proposed model achieves the desired domain transfer while maintaining general ability and highest utilization of available resources.
CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting (2024.lrec-main)

Copied to clipboard

Challenge: End-to-end automatic speech recognition systems struggle to recognize rare name entities such as personal names, organizations and terminologies that are not frequently encountered in the training data.
Approach: They propose a convolutional neural network-based ASR system that performs open-vocabulary keyword-spotting before the decoder to match the features between the entities and the utterances.
Outcome: The proposed system significantly improves mixed-error-rate (MER) and entity recall compared to the original Whisper model on three internal datasets and two publicly available datasets.
AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have advanced the automation of data science workflows, yet it remains unclear whether they can critically leverage external domain knowledge as human data scientists do in practice.
Approach: They propose a benchmark to evaluate how large language models handle external domain knowledge in tabular prediction tasks.
Outcome: The proposed model evaluates whether it can critically leverage external domain knowledge as human data scientists do in practice.
Reaction Miner: An Integrated System for Chemical Reaction Extraction from Textual Data (2023.emnlp-demo)

Copied to clipboard

Challenge: Reaction Miner is a system designed to extract chemical reactions from raw scientific PDFs.
Approach: They propose a system that extracts chemical reactions directly from raw scientific PDFs.
Outcome: The proposed system can extract chemical reactions from raw scientific PDFs.
What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension (2021.findings-emnlp)

Copied to clipboard

Challenge: Explicit Span-Sentence Predication solves location unit ambiguity problem in many languages, allowing model to determine which sentence contains the answer span when sentence itself has not been clearly defined at all.
Approach: They propose a machine-learning reader with Explicit Span-Sentence Predication to solve this problem by analyzing Chinese sentences.
Outcome: The proposed reader achieves state-of-the-art on Chinese MRC benchmark and shows great potential in dealing with other languages.
TokenPenalty: Alleviating Attention Sinks and Positional Decay in LVLMs (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) often hallucinate due to two relevant phenomena: massive activation phenomenon and positional information decay.
Approach: They propose a token-level intervention strategy that dynamically suppresses irrelevant visual tokens while preserving key contextual signals.
Outcome: Experiments show that TokenTruth significantly improves factual consistency across MLLMs on standard image understanding benchmarks.
Mutual-Learning Improves End-to-End Speech Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to end-to-end speech translation (E2E) models only allow one way knowledge transfer, which is limited by the performance of the teacher model.
Approach: They propose a one-way knowledge transfer paradigm where the MT and ST models are collaboratively trained and considered as peers rather than teacher/student.
Outcome: The proposed model improves the performance of end-to-end speech translation (ST) task by combining knowledge from two models with peer models.
ArT: All-round Thinker for Unsupervised Commonsense Question Answering (2022.coling-1)

Copied to clipboard

Challenge: Existing work on commonsense QA requires labeled training data for its success . existing work relies on large-scale in-domain or out-of-domain labeles or fails to generate knowledge of high quality in a general way.
Approach: They propose an approach to commonsense question-answering (QA) that takes association during knowledge generation.
Outcome: The proposed model outperforms existing models on commonsense QA benchmarks.
Instruct and Extract: Instruction Tuning for On-Demand Information Extraction (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models with instruction-following capabilities are not suitable for long-tail ad hoc extraction use cases for non-expert users.
Approach: They propose a task that follows instructions to extract the desired content from the associated text and present it in a structured tabular format.
Outcome: The proposed paradigm outperforms existing open-source models of similar size in terms of information extraction.
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)

Copied to clipboard

Challenge: Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks.
Approach: They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk.
Outcome: The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets.
T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Copied to clipboard

Challenge: Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach: They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome: The proposed model improves in simple and complex scenarios with AI feedback learning.
CoTD-PO: Chain-of-Thought Distillation with Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for chain-of-thought distillation suffer from a distribution mismatch between teacher-generated training trajectories and the student model's own generative distribution.
Approach: They propose a framework that shifts the training paradigm from passive imitation to active trajectory exploration by allowing students to sample their own answer paths.
Outcome: The proposed method outperforms standard CoT distillation baselines while mitigating mode collapse and preserving semantic diversity.
Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction (2024.findings-eacl)

Copied to clipboard

Challenge: Existing frameworks for fine-grained few-shot entity extraction are difficult to implement in the chemical domain due to the information overload of scientific papers.
Approach: They propose a sequence-to-sequence based few-shot entity extraction approach . it uses a seq2seq entity extractor and a self-validation module to reconstruct original input sentence .
Outcome: The proposed framework achieves 8.26% and 6.84% performance gains on two datasets.
SQL Injection Jailbreak: A Structural Disaster of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to jailbreak Large Language Models (LLMs) exploited internal properties or capabilities of the model, such as optimization-based jailbreak methods and methods that leveraged the model’s context-learning abilities.
Approach: They propose a new method which injects jailbreak information into user prompts and induces the model to generate harmful content.
Outcome: The proposed method achieves near 100% success rates on open-source models while incurring lower time costs compared to previous methods.
Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification (2023.acl-long)

Copied to clipboard

Challenge: Recent methods for event schema induction use information extraction systems to construct event graph instances from documents . compared to the previous state-of-the-art closed-domain schema inducing model, human assessors were able to cover 10% more events when translating the schemas into coherent stories .
Approach: They propose to treat event schemas as commonsense knowledge that can be derived from large language models.
Outcome: The proposed method simplifies the schema induction process and improves readability.
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs .
Approach: They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service .
Outcome: The proposed benchmark evaluates the security of RAG against 14 representative RAG components.
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach: They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome: The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.

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