Papers by Helen Li

6 papers
Rethinking Machine Ethics – Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? (2024.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to making moral judgments are mostly bottom-up and lack explainability.
Approach: They propose a top-down framework to steer Large Language Models to perform moral reasoning with well-established moral theories.
Outcome: The proposed framework can integrate various moral theories on moral datasets.
Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to incorporate retriever’s preference during the training of query rewriting models rely on extensive annotations such as in-domain rewrites and/or relevant passage labels, limiting their generalization and adaptation capabilities.
Approach: They propose a framework for training query rewriting models with limited rewrite annotations from seed datasets and completely no passage label.
Outcome: The proposed approach decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retrievers.
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach: They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome: The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.
SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting (2023.findings-emnlp)

Copied to clipboard

Challenge: Experimental results show that SGP-TOD provides state-of-the-art zero-shot performance . prevailing approach for creating task bots is to fine-tune pre-trained language models .
Approach: They propose a Schema-Guided Prompting for building Task-Oriented Dialog systems . they use predefined task schema and dialog policy to instruct fixed LLMs to generate appropriate responses .
Outcome: The proposed system outperforms few-shot approaches on multiwoz, RADDLE, and STAR datasets.
Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark (2022.findings-emnlp)

Copied to clipboard

Challenge: a number of safety concerns hinder the deployment of open-domain dialog systems, such as offensive languages and toxic behaviors, such social bias is difficult to detect.
Approach: They propose a Dial-Bias Framework for analyzing social bias in conversations . they introduce a Chinese social bias dialog dataset and conduct in-depth ablation studies .
Outcome: The proposed framework is the first annotated Chinese social bias dialog dataset . the proposed framework also provides a fine-grained dialog bias measurement benchmark .
Disentangling Indirect Answers to Yes-No Questions in Real Conversations (2022.naacl-main)

Copied to clipboard

Challenge: Existing models with synthetic indirect answers to yes-no questions are not beneficial when working with real conversations.
Approach: They propose to annotate the underlying direct answers to yes-no questions in real conversations.
Outcome: The proposed model outperforms the majority baseline but the task remains a challenge.

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