Papers by Jane Dwivedi-Yu

9 papers
Efficient Tool Use with Chain-of-Abstraction Reasoning (2025.coling-main)

Copied to clipboard

Challenge: Recent large language models have made progress at interpreting and executing instructions.
Approach: They propose a method to decouple general reasoning from specialized knowledge . they propose to use abstract reasoning chains and domain tools to reify each chain .
Outcome: The proposed method outperforms baseline methods on QA and mathematical reasoning domains.
Active Learning Principles for In-Context Learning with Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: In-context learning has significantly enhanced predictive performance in few-shot learning settings.
Approach: They propose to use pool-based Active Learning to identify the most informative demonstrations for few-shot learning over a single iteration to identify best demonstrations.
Outcome: The proposed model outperforms all other methods, including random sampling, in the analysis of 24 classification and multi-choice tasks.
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.
Measuring and Addressing Indexical Bias in Information Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Information Retrieval (IR) systems may not optimize rankings for fairness, neutrality, or the balance of ideas.
Approach: They propose to use a framework to automatically audit IR rankings for indexical biases, or biase in the positional order of documents.
Outcome: The proposed bias metric can help predict when and how indexical bias will shift a reader’s opinion.
TOOLVERIFIER: Generalization to New Tools via Self-Verification (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing tools and APIs present a challenge for generalization, despite frequent parameter updates and the daily introduction of new tools.
Approach: They propose a method which distinguishes between close candidates by self-asking contrastive questions during tool selection and parameter generation.
Outcome: Experiments on 4 tasks from the ToolBench benchmark show an improvement of 22% over few-shot baselines.
TimelineQA: A Benchmark for Question Answering over Timelines (2023.findings-acl)

Copied to clipboard

Challenge: Existing question answering techniques for lifelogs do not provide accurate answers . augmented reality glasses have led to the creation of personal assistants .
Approach: They propose to use a benchmark to query lifelogs to find out what happened in real life . they find that extractive QA systems out-perform retrieval-augmented QA techniques .
Outcome: The proposed method outperforms state-of-the-art retrieval-augmented QA systems in atomic queries and multi-hop queries.
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.
ROBBIE: Robust Bias Evaluation of Large Generative Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: generative large language models (LLMs) are becoming more performant and prevalent . we need tools to measure and improve their fairness, authors say .
Approach: They propose to compare 6 different prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative large language models.
Outcome: The proposed model can be tested on more datasets to better characterize and mitigate biases . the study compared 6 prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative large language models.
Active Retrieval Augmented Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Generative language models (LMs) have a tendency to hallucinate and create inaccurate output.
Approach: They propose a method which iteratively uses a prediction of the upcoming sentence to anticipate future content.
Outcome: The proposed method achieves superior or competitive performance on all tasks . iteratively uses a prediction of the upcoming sentence to anticipate future content .

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