Papers by Lijie Wang

21 papers
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies have shown that large language models implicitly embed reasoning trees, but their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations.
Approach: They propose to use circuit analysis and self-influence functions to map the reasoning process of large models.
Outcome: The proposed model is able to map human-interpretable reasoning paths and a model's underlying circuits reveal human-mediated reasoning processes.
Syntax-guided Contrastive Learning for Pre-trained Language Model (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies rely on additional syntax-driven attention components to enhance the transformer, which require more parameters and additional syntactic parsing in downstream tasks.
Approach: They propose a syntax-guided contrastive learning method which does not change the transformer architecture and does not alter the transformer structure.
Outcome: The proposed method achieves consistent improvements in a variety of tasks including grammatical error detection, entity tasks, structural probing and GLUE.
Automatic Table Union Search with Tabular Representation Learning (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to identify uniability based on column representations are insufficient to reveal latent relational features to describe column relation between pair of columns.
Approach: They propose a self-supervised table union search framework called AutoTUS to learn column relational representations in a multi-stage manner.
Outcome: The proposed framework improves on the SOTA baseline and on real-world datasets.
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)

Copied to clipboard

Challenge: Current sycophancy research has largely overlooked its specific manifestations in the video-language domain.
Approach: They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs.
Outcome: The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks.
Improving Preference Alignment of LLM with Inference-Free Self-Refinement (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning.
Approach: Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning.
Outcome: Experiments show that incorporating IFSR into preference alignment yields performance improvement over 10%.
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach: They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome: The proposed method bridges psychological value frameworks with neuron analysis in large language models.
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images (2026.acl-long)

Copied to clipboard

Challenge: Existing methods require explicit safety labels or contrastive data, yet visual inputs enable harmful outputs.
Approach: They propose a visual self-fulfilling alignment mechanism that fine-tunes vision-language models on neutral VQA tasks without any safety labels.
Outcome: The proposed approach reduces attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities.
Private Language Models via Truncated Laplacian Mechanism (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for word embedding are prone to privacy leakage, resulting in weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength.
Approach: They propose a method for private word embedding that uses a non-trivial extension of the truncated Laplacian mechanism and propose to test its effectiveness.
Outcome: The proposed method has lower variance compared to the previous methods.
COMPKE: Complex Question Answering under Knowledge Editing (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for knowledge editing do not accurately evaluate how well models apply knowledge in real-life situations.
Approach: They propose a benchmark to evaluate how well updated models apply new knowledge in real-life situations.
Outcome: The proposed method achieves 39.47 accuracy on GPT-4o-mini but drops significantly to 3.83 on Qwen2.5-3B.
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.
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to evaluate preference data without human annotations are difficult . et al., 2022b) is effective for aligning large language models with human expectations .
Approach: They propose a method to evaluate the response preference using output probabilities under contrastive prompts.
Outcome: The proposed method could surpass the RLHF method without human-annotated preference data.
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)

Copied to clipboard

Challenge: Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts.
Approach: They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships.
Outcome: The proposed model improves in role-play settings and in e-commerce and recommendation systems.
Differentially Private Natural Language Models: Recent Advances and Future Directions (2024.findings-eacl)

Copied to clipboard

Challenge: Recent advances in deep learning have led to great success in various natural language processing tasks.
Approach: They propose a systematic review of recent advances in DP deep learning models . they discuss some differences and additional challenges of DP-NLP .
Outcome: The proposed method can prevent reconstruction attacks and protect against potential side knowledge while maintaining the privacy of sensitive data.
Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear.
Approach: They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models.
Outcome: The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters.
Understanding the Repeat Curse in Large Language Models from a Feature Perspective (2025.findings-acl)

Copied to clipboard

Challenge: Large language models suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”.
Approach: They propose a method to induce and analyze the Repeat Curse in large language models by using mechanistic interpretability.
Outcome: The proposed method induces and analyzes the Repeat Curse in large language models using mechanistic interpretability.
Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing data on suicidal ideation in private conversations are limited . a new dataset of 1,200 test cases is presented to address this gap .
Approach: They propose a dataset of 1,200 test cases simulating implicit suicidal ideation in private contexts.
Outcome: The proposed dataset includes 1,200 test cases simulating implicit suicidal ideation in dialogue scenarios.
Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach: They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome: The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset (2020.emnlp-main)

Copied to clipboard

Challenge: Existing text-to-SQL parsing methods mainly focus on English, but there is no labeled data available for the language . a larges-scale and pragmatic Chinese dataset is used for cross-domain text- to-Sql task .
Approach: They propose a larges-scale Chinese dataset for a cross-domain text-to-SQL task . they analyze questions from several representative applications and use an effective data construction framework .
Outcome: The proposed dataset contains 200 databases, 813 tables, and 23,797 question/SQL pairs.
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to parse text-to-SQL data are lacking labeled data for unseen evaluation databases.
Approach: They propose a framework for enhancing SQL queries by automatically producing large numbers of SQL queries based on an abstract syntax tree grammar.
Outcome: The proposed framework can produce high-quality natural language questions over strong baselines.
IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding (2023.findings-emnlp)

Copied to clipboard

Challenge: Instance attribution (IA) aims to identify the training instances leading to the prediction of a test example.
Approach: They propose a systematic and comprehensive evaluation scheme covering four significant requirements: sufficiency, completeness, stability and plausibility.
Outcome: The proposed evaluation scheme covers four significant requirements: sufficiency, completeness, stability and plausibility.
IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models (2023.emnlp-main)

Copied to clipboard

Challenge: Using manual data analysis, dataset refinement approaches are often unable to cover all the potential biased features.
Approach: They propose an iterative bias-aware dataset refinement framework which debiases NLU models without predefining biased features.
Outcome: The proposed framework outperforms existing methods and is compatible with model-centric methods.

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