2.3k citations · 4.7k across the 88 of their papers we have counts for
40 papers · 1 filter
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Lionel Wong, Gabriel Grand, Alexander K. Lew +4
How does language inform our downstream thinking? In particular, how do humans make meaning from language--and how can we leverage a theory of linguistic meaning to build machines…
Understanding Social Reasoning in Language Models with Language Models
Kanishk Gandhi, Jan-Philipp Fränken, Tobias Gerstenberg +1
As Large Language Models (LLMs) become increasingly integrated into our everyday lives, understanding their ability to comprehend human mental states becomes critical for ensuring…
Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems
Dhara Yu, Noah D. Goodman, Jesse Mu
Humans teach others about the world through language and demonstration. When might one of these modalities be more effective than the other? In this work, we study the factors that…
Overinformative Question Answering by Humans and Machines
Polina Tsvilodub, Michael Franke, Robert D. Hawkins +1
When faced with a polar question, speakers often provide overinformative answers going beyond a simple "yes" or "no". But what principles guide the selection of additional informat…
Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
Zhengxuan Wu, Atticus Geiger, Thomas Icard +2
Obtaining human-interpretable explanations of large, general-purpose language models is an urgent goal for AI safety. However, it is just as important that our interpretability met…
Solving Math Word Problems by Combining Language Models With Symbolic Solvers
Joy He-Yueya, Gabriel Poesia, Rose E. Wang +1
Automatically generating high-quality step-by-step solutions to math word problems has many applications in education. Recently, combining large language models (LLMs) with externa…
Learning to Compress Prompts with Gist Tokens
Jesse Mu, Xiang Lisa Li, Noah Goodman
Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding…
Task Ambiguity in Humans and Language Models
Alex Tamkin, Kunal Handa, Avash Shrestha +1
Language models have recently achieved strong performance across a wide range of NLP benchmarks. However, unlike benchmarks, real world tasks are often poorly specified, and agents…
Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
Eric Zelikman, Qian Huang, Gabriel Poesia +2
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans…
Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models
Ben Prystawski, Paul Thibodeau, Christopher Potts +1
Probabilistic models of language understanding are valuable tools for investigating human language use. However, they need to be hand-designed for a particular domain. In contrast,…
Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning
Fei Fang, Kunal Sinha, Noah D. Goodman +2
Speakers' referential expressions often depart from communicative ideals in ways that help illuminate the nature of pragmatic language use. Patterns of overmodification, in which a…
Mixed-effects transformers for hierarchical adaptation
Julia White, Noah Goodman, Robert Hawkins
Language use differs dramatically from context to context. To some degree, modern language models like GPT-3 are able to account for such variance by conditioning on a string of pr…
Language modeling via stochastic processes
Rose E Wang, Esin Durmus, Noah Goodman +1
Modern language models can generate high-quality short texts. However, they often meander or are incoherent when generating longer texts. These issues arise from the next-token-onl…
Causal Distillation for Language Models
Zhengxuan Wu, Atticus Geiger, Josh Rozner +5
Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student mo…
Open-domain clarification question generation without question examples
Julia White, Gabriel Poesia, Robert Hawkins +2
An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans. However, natural language can be ambiguous or unclear. In cases of u…
Calibrate your listeners! Robust communication-based training for pragmatic speakers
Rose E. Wang, Julia White, Jesse Mu +1
To be good conversational partners, natural language processing (NLP) systems should be trained to produce contextually useful utterances. Prior work has investigated training NLP…
Learning to solve complex tasks by growing knowledge culturally across generations
Michael Henry Tessler, Jason Madeano, Pedro A. Tsividis +3
Knowledge built culturally across generations allows humans to learn far more than an individual could glean from their own experience in a lifetime. Cultural knowledge in turn res…
Emergent Communication of Generalizations
Jesse Mu, Noah Goodman
To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games. However…
Concadia: Towards Image-Based Text Generation with a Purpose
Elisa Kreiss, Fei Fang, Noah D. Goodman +1
Current deep learning models often achieve excellent results on benchmark image-to-text datasets but fail to generate texts that are useful in practice. We argue that to close this…
From partners to populations: A hierarchical Bayesian account of coordination and convention
Robert D. Hawkins, Michael Franke, Michael C. Frank +4
Languages are powerful solutions to coordination problems: they provide stable, shared expectations about how the words we say correspond to the beliefs and intentions in our heads…
Language Through a Prism: A Spectral Approach for Multiscale Language Representations
Alex Tamkin, Dan Jurafsky, Noah Goodman
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these sc…
Learning to refer informatively by amortizing pragmatic reasoning
Julia White, Jesse Mu, Noah D. Goodman
A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information. One theory for how humans reason about language is presented in…
Investigating Transferability in Pretrained Language Models
Alex Tamkin, Trisha Singh, Davide Giovanardi +1
How does language model pretraining help transfer learning? We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance…
Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks
Robert D. Hawkins, Noah D. Goodman, Adele E. Goldberg +1
A key property of linguistic conventions is that they hold over an entire community of speakers, allowing us to communicate efficiently even with people we have never met before. A…