Papers by Brandon Stewart

5 papers
AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments (2024.emnlp-main)

Copied to clipboard

Challenge: Existing tools for persuasion are well-equipped to identify which of a pre-existing set of messages is most persuasive, but they do not offer causal evidence on whether or how they have succeeded.
Approach: They propose a framework for identifying topical components of persuasive arguments that are autopersuade.
Outcome: The proposed framework validates the results through human studies and out-of-sample predictions.
GPT Deciphering Fedspeak: Quantifying Dissent Among Hawks and Doves (2023.findings-emnlp)

Copied to clipboard

Challenge: We use GPT-4 to quantify dissent among members on the topic of inflation . transcripts and minutes reflect the diversity of member views in a way that is lost or omitted from the public statements.
Approach: They use transcripts and minutes to quantify dissent among FOMC members . they find that transcripts reflect diversity of member views in a way that is lost or omitted .
Outcome: The proposed method better captures extremes, which mirror human annotations, and suggests that Large Language Models can avoid noise in this nuanced context.
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors (P18-1)

Copied to clipboard

Challenge: Existing word2vec-based methods for learning rare or unseen words have been criticized for degrading performance in small corpus settings.
Approach: They propose a la carte embedding method that relies on a linear transformation that is efficiently learnable using pretrained word vectors and linear regression.
Outcome: The proposed method is based on a new dataset showing that it can be used when a word is encountered even if only a single usage example is available.
Credible without Credit: Domain Experts Assess Generative Language Models (2023.acl-short)

Copied to clipboard

Challenge: ChatGPT has been criticized for its lack of accuracy and coherence . authors argue that language models could replace search engines and make college essays obsolete .
Approach: a team of 10 domain experts conducts an initial assessment of language models using 100 expert-written questions.
Outcome: The results show that language models are mixed in their accuracy.
More Victories, Less Cooperation: Assessing Cicero’s Diplomacy Play (2024.acl-long)

Copied to clipboard

Challenge: Diplomacy is a boardgame that offers a challenge for communicative and cooperative AI.
Approach: They run two dozen games with Cicero and annotate in-game communication with abstract meaning representation to separate in- game tactics from general language.
Outcome: The proposed method can outperform Cicero in communicating with humans, but it's difficult to deceive and persuade AI.

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