Papers by Jian Lou

10 papers
Task Oriented In-Domain Data Augmentation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for large language models suffer from two major issues: in-domain data are scarce compared with general domain-agnostic data.
Approach: They propose a task-oriented in-domain data augmentation framework that uses in- domain data selection and task-orientated synthetic passage generation to adapt LLMs to two domains: advertisement and math.
Outcome: The proposed framework improves LLM performance by 8% in the advertisement domain and 7.5% in the math domain.
Don’t Say No: Jailbreaking LLM by Suppressing Refusal (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are vulnerable to "jailbreaking" attacks where crafted prompts manipulate them into producing toxic content.
Approach: They propose to improve the target loss objective by combining a cosine decay schedule method with refusal suppression to achieve higher success rates.
Outcome: The proposed approach outperforms baseline attacks and achieves state-of-the-art attack success rates.
Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training (2025.findings-emnlp)

Copied to clipboard

Challenge: Adversary-aware DPO (ADPO) is a training framework that explicitly considers adversary.
Approach: a new framework integrates adversarial training into a pre-trained large language model to enhance safety alignment . adversary-aware DPO provides a framework that explicitly considers adversary .
Outcome: a new training framework outperforms baselines in safety alignment and general utility of large language models.
Token-level Inference-Time Alignment for Vision-Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity . despite widespread adoption, VLMs often exhibit a critical failure mode: hallucination .
Approach: They propose a framework for Token-level Inference-Time Alignment that steers the decoding process without updating the base model parameters.
Outcome: The proposed framework improves performance on 13 benchmarks across architectures . it boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score .
Certified Robustness to Word Substitution Attack with Differential Privacy (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies have shown that adversarial examples can be easily fooled by DNNs, making the robustness and security of NLP models significantly important.
Approach: They propose a differential privacy-based algorithm to achieve certified robustness against word substitution at- tacks in text classification via differential privacy.
Outcome: The proposed model achieves higher accuracy and more than 30X efficiency improvement over existing defense algorithms.
TACR: A Table Alignment-based Cell Selection Method for HybridQA (2023.findings-acl)

Copied to clipboard

Challenge: Hybrid Question-Answering datasets lack a robust reasoning model for text-based QA.
Approach: They propose a table-question-alignment-based cell-selection and reasoning model for hybrid text and table QA.
Outcome: The proposed model outperforms baselines on HybridQA and WikiTableQuestions datasets on cell selection and argumentation.
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
Approach: They propose a dual-alignment pre-training framework that incorporates both sentence-level and token-level alignment.
Outcome: The proposed framework improves cross-lingual sentence embedding on three cross-linguistic benchmarks.
FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers.
Approach: They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning .
Outcome: The proposed model achieves competitive performance with frontier models while maintaining generation efficiency.
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications (D18-1)

Copied to clipboard

Challenge: Existing approaches to generate programs from natural language do not address program aliasing . semantically equivalent programs may have many syntactically different forms .
Approach: They propose a semantics-based approach to generate regular expressions from natural language.
Outcome: The proposed approach improves on three public datasets.
The Model Agreed, But Didn’t Learn: Diagnosing Surface Compliance in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models internalize vast world knowledge as parametric memory, yet inherit the staleness and errors of their source corpora.
Approach: They propose a framework that subjects models to discriminative self-assessment under diverse contextual pressures to scrutinize subtle behavioral nuances induced by memory modifications.
Outcome: The proposed framework achieves high benchmarks without overwriting internal beliefs, while recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model’s memory state.

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