Papers by Xiaolin Li

6 papers
Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe.
Approach: They propose a methodology that embeds harmful requests within ethical framings to exploit this vulnerability.
Outcome: The proposed framework achieves high success rates by exploiting model's own ethical reasoning to frame harmful actions as morally necessary compromises.
Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)

Copied to clipboard

Challenge: Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers.
Approach: They constructed a dataset which contains a corresponding reference summary for each original lengthy answer.
Outcome: The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset.
A Batch Normalized Inference Network Keeps the KL Vanishing Away (2020.acl-main)

Copied to clipboard

Challenge: Variational Autoencoder (VAE) is widely used to approximate a model’s posterior on latent variables.
Approach: They propose to let the Kullback–Leibler divergence individual follow a distribution across the whole dataset and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL’s distribution positive.
Outcome: The proposed approach can avoid posterior collapse effectively and efficiently without introducing any new model component or modifying the objective.
GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model (D18-1)

Copied to clipboard

Challenge: Conventional topic models suffer different problems in different settings.
Approach: They propose a novel way to model word-pairs named biterms in the whole corpus and a Graph Convolutional Networks (GCNs) with residual connections to extract transitive features from biterm.
Outcome: The proposed model generates more coherent topics compared with previous methods.
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs (2026.acl-long)

Copied to clipboard

Challenge: Large language models exhibit strong general reasoning abilities, yet the community lacks controllable, scalable, and verifiable tools to analyze and improve them.
Approach: They propose a verifier that generates diverse SAT-based reasoning tasks from CNF instances and checks answers objectively with PySAT.
Outcome: The proposed verifier generates diverse SAT-based reasoning tasks from CNF instances and checks answers objectively with PySAT.
DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization (D19-1)

Copied to clipboard

Challenge: Existing models for natural language video localization are top-down and bottom-up . however, both approaches suffer several limitations, leading to performance degradation .
Approach: They propose a top-down approach for localizing a natural language description in a video sequence . they propose 'DEnse Bottom-Up Grounding' which uses the temporal boundaries of each video frame .
Outcome: The proposed framework matches the speed of top-down models while surpassing the state-of-the-art models.

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