Papers by Yi-Chia Wang

7 papers
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming (2024.naacl-long)

Copied to clipboard

Challenge: Existing red-teaming methods for large language models often discover safety risks without addressing them.
Approach: They propose a multi-round automatic red-teaming method that incorporates both adversarial prompt writing and safe response generation.
Outcome: The proposed method significantly increases red-teaming scalability and the safety of the target LLM.
Controllable Text Generation with Focused Variation (2020.findings-emnlp)

Copied to clipboard

Challenge: Focused-Variation Network (FVN) is a new model to control language generation.
Approach: They propose a model that learns discrete latent spaces for each attribute inside codebooks and uses them to generate fluent text.
Outcome: The proposed model can generate fluent and mostly coherent text on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.
NormBank: A Knowledge Bank of Situational Social Norms (2023.acl-long)

Copied to clipboard

Challenge: NormBank is a knowledge bank of 155k situational norms that can be used to ground flexible normative reasoning for interactive, assistive, and collaborative AI systems.
Approach: They propose a new scheme for hierarchically organizing the seemingly unbounded social norms within a multivalent sociocultural frame.
Outcome: The proposed framework can be used to ground flexible reasoning for interactive, assistive, and collaborative AI systems.
The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems (2022.acl-long)

Copied to clipboard

Challenge: Moral integrity corpus captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs).
Approach: They propose a resource that captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs).
Outcome: The proposed resource captures the moral assumptions of 38k prompt-reply pairs, using 99k distinct Rules of Thumb (RoTs).
Generating Hashtags for Short-form Videos with Guided Signals (2023.acl-long)

Copied to clipboard

Challenge: Short-form video hashtag recommendation (SVHR) is a classification or ranking problem that selects hashtags from a set of limited candidates.
Approach: They propose a short-form video hashtag recommendation task that better represents how hashtags are created naturally by retrieving relevant hashtags from a large-scale hashtag pool as extra guidance signals.
Outcome: The proposed model outperforms strong classification baselines on two short-form video datasets and the guidance signals boost the performance by 8.11 and 2.17 absolute ROUGE-1 scores on average.
COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation (2023.emnlp-main)

Copied to clipboard

Challenge: Personalized text generation (PTG) is a key component of our digital lives but can inadvertently associate different levels of linguistic quality with users’ protected attributes.
Approach: They propose a framework to achieve measure-specific counterfactual fairness in explanation generation by focusing on one of the most studied settings: generating natural language explanations for recommendations.
Outcome: The proposed framework achieves measure-specific counterfactual fairness in explanation generation.
Extrapolating to Unknown Opinions Using LLMs (2025.coling-main)

Copied to clipboard

Challenge: ice cream flavors and climate change are among the topics people hold on various topics.
Approach: They propose to use a large language model to extrapolate from stances to unknown opinions by prompting and fine-tuning data to improve their ability to extrapole from known to unknown stance.
Outcome: The proposed model can extrapolate from opinions on known topics to unknown ones and generate reasoning behind extrapolation.

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