AAAI/EAAI Patrick Henry Winston Outstanding Educator Award: T(w)eaching AI in the Age of LLMs

Mechanistic interpretability is one of the most exciting and important research programs in current AI. My aim is to build some philosophical foundations for the program, along with setting out some concrete challenges and assessing progress to date. I will argue for the importance of propositional interpretability, which involves interpreting a system’s mechanisms and behavior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probability) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems log all of the relevant propositional attitudes in an AI system over time. I will examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including psychosemantics and representation theorems) to assess their strengths and weaknesses as methods of propositional interpretability.

Propositional Interpretability in Humans and AI Systems

Can AI Benefit Humanity?

Spatial reasoning is a core component of an agent’s ability to operate in or reason about the physical world. LLMs are widely promoted as having abilities to reason about a wide variety of domains, including commonsense. In this talk I will discuss the ability of state-of-the-art LLMs to perform commonsense reasoning, particularly with regard to spatial information. Across a wide range of LLMs, although they show abilities rather better than chance, they still struggle with many questions and tasks, for example when reasoning about directions, or topological relations.

Can Large Language Models Reason about Spatial Information?

In this keynote, Andrew will explore how current technologies, particularly agentic workflow, are revolutionizing the development of AI products. He will also delve into the role of AI in prototyping, showcasing how AI lowers the cost of software development and accelerates the prototyping process.

AI, Agents and Applications

This talk focuses on the use of foundation models to study problems in labor economics, in particular problems relating to the progression of worker careers and wages. In Vafa et al. (2024a), we introduced a transformer-based predictive model, CAREER, that predicts a worker’s next job as a function of career history (an “occupation model”). CAREER was initially estimated (“pre-trained”) using a large, unrepresentative resume dataset, which served as a “foundation model,” and parameter estimation was continued (“fine-tuned”) using data from a representative survey. CAREER had better predictive performance than benchmarks. Athey et al (2024) considers an alternative where the resume-based foundation model is replaced by a large language model (LLM). We convert tabular data from the survey into text files that resemble resumes and fine-tune the LLMs using these text files with the objective to predict the next token (word). The resulting fine-tuned LLM is used as an input to an occupation model. Its predictive performance surpasses all prior models. We demonstrate the value of fine-tuning and further show that by adding more career data from a different population, fine-tuning smaller LLMs surpasses the performance of fine-tuning larger models. In Vafa et al. (2024b), we apply and adapt this framework to the problem of gender wage decompositions, which require estimating the portion of the gender wage gap explained by career histories of workers. Classical methods for decomposing the wage gap employ simple linear models, and the resulting decompositions thus suffer from omitted variable bias (OVB), where covariates that are correlated with both gender and wages are not included in the model. We explore an alternative methodology for wage gap decomposition that employs CAREER as a foundation model. We prove that the way foundation models are usually trained might still lead to OVB, but develop fine-tuning algorithms that empirically mitigate this issue. We first provide a novel set of conditions under which an estimator of the wage gap based on a fine-tuned foundation model is root-n-consistent. Building on the theory, we then propose methods for fine-tuning foundation models that minimize OVB. Using data from the Panel Study of Income Dynamics, we find that history explains more of the gender wage gap than standard econometric models can measure, and we identify elements of history that are important for reducing OVB.

Predicting Career Transitions and Estimating Wage Disparities Using Foundation Models

Natural language serves as the primary mode of communication when an intelligent agent with a physical presence engages with human beings. While a plethora of research focuses on natural language understanding (NLU), encompassing endeavors such as sentiment analysis, intent prediction, question answering, and summarization, the scope of NLU directed at situations necessitating tangible actions by an embodied agent remains limited. The inherent ambiguity and incompleteness inherent in natural language present challenges for intelligent agents striving to decipher human intention. To tackle this predicament head-on, we introduce a novel system known as \textbf{t}ask and \textbf{a}rgument \textbf{g}rounding for \textbf{E}mbodied agents (\system). At its core, our system employs an inventive neural network model designed to extract a series of tasks from complex task instructions expressed in natural language. Our proposed model adopts an encoder-decoder framework enriched with nested decoding to effectively extract tasks and their corresponding arguments from these intricate instructions. These extracted tasks are then mapped (or grounded) to the robot's established collection of skills, while the arguments find grounding in objects present within the environment. To facilitate the training and evaluation of our system, we have curated a dataset featuring complex instructions. The results of our experiments underscore the prowess of our approach, as it outperforms robust baseline models.

tagE: Enabling an Embodied Agent to Understand Human Instructions​

A key contribution to being a successful researcher in natural language processing, as in any area, is having a clear overarching vision of what your body of research is trying to accomplish. Using my own 40-year career as an example, I will attempt to provide general advice on formulating and pursuing a coherent research vision. In particular, I will focus on formulating a unique, personal objective that exploits your specific talents, knowledge, and passions, and that is distinct from the current popular trends in the field. I will also focus on formulating a vision that bridges existing fields of study to produce an overarching agenda that unifies previously disparate ideas.

The Vision Thing: Finding and Pursuing your Research Passion

Transliteration is very important in the Indian
language context due to the usage of multi-
ple scripts and the widespread use of roman-
ized inputs. However, few training and evalu-
ation sets are publicly available. We introduce
Aksharantar1, the largest publicly available
transliteration dataset for Indian languages cre-
ated by mining from monolingual and paral-
lel corpora, as well as collecting data from hu-
man annotators. The dataset contains 26 mil-
lion transliteration pairs for 21 Indic lan-
guages from 3 language families using 12
scripts. Aksharantar is 21 times larger than ex-
isting datasets and is the first publicly available
dataset for 7 languages and 1 language fam-
ily. We also introduce the Aksharantar testset
comprising 103k word pairs spanning 19 lan-
guages that enables a fine-grained analysis of
transliteration models on native origin words,
foreign words, frequent words, and rare words.
Using the training set, we trained IndicXlit,
a multilingual transliteration model that im-
proves accuracy by 15% on the Dakshina test
set, and establishes strong baselines on the Ak-
sharantar testset introduced in this work. The
models, mining scripts, transliteration guide-
lines, and datasets are available at https://
github.com/AI4Bharat/IndicXlit under
open-source licenses.

Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users

**Abstract:**

Social learning is a key driver of the success of the human species (Henrich, 2015), enabling the preservation of technologies that individuals could not possibly have acquired on their own (Tennie, Call, & Tomasello, 2009). Presently, we are witnessing the rise of intelligent machines – “AI systems” – that are capable of making discoveries beyond the human horizon (Wang et al., 2023). This raises the question of whether social learning enables humans to also adopt and preserve inconceivable discoveries made by intelligent machines. In our behavioral experiment, participants’ success in a strategic task hinged on adopting a solution that humans struggle to discover due to a characteristic bias to avoid large losses. We contrast populations of humans transmitting solutions over multiple generations on their own with populations that had the opportunity to learn from AI agents in their first generation. Our findings show that an algorithmic model succeeds in discovering the adaptive strategy where humans fail on their own. Most importantly, humans are able to adopt this machine-introduced strategy and preserve it over multiple generations. Taken together, our results showcase the potential of intelligent machines to transform human cultural evolution, and an opportunity for designing them towards benefitting human progress.

**Speaker's social media:**

Twitter: @ThomasF_Mueller
Bluesky: @thomasfmueller.bsky.social

LIVE - Humans can learn and culturally preserve inconceivable strategies discovered by intelligent machines

**Abstract:**

This project looks at whether cooperation and storytelling have co-evolved. Debates continue over the extent to which widespread cooperation in humans can be explained by the mechanisms that maintain it in other species, such as kin selection and reciprocity. Storytelling may help reinforce large-scale cooperation by transmitting prosocial norms and acting as a social ‘flight simulator’. Previous evidence from transmission chain experiments suggests a bias towards social information in narratives, but the co-evolution of storytelling and cooperation remains understudied.  

This project looked at how prosocial behaviours were viewed within folktales and if prosocial moral messages were more widespread in folktales. To determine this, 452 people read 300 Indo-European folktales and commented on the moral messaging and moral behaviours found within them. It was found that cooperative behaviours such as altruism, reciprocity, helping family were viewed significantly more positively while individualistic behaviours were found to be viewed significantly more negatively. Significantly more stories were rated as having a prosocial main moral message than an individualistic one. This project aims to undertake future projects using phylogenetic comparative methods and experimental research, investigating whether prosociality in stories affects transmission fidelity and cooperative behaviour itself.


**Speaker's social media:**

em_ilyjxx 
emilymljeffries.bsky.social

The Moral of the Story - Investigating the co-evolution of storytelling and Human Cooperation via a survey of moral attitudes to Indo-European folktales

**Abstract:**

Language provides humans a remarkably flexible and abstract way to transmit information. Here, we tested the hypothesis that language allows cultural evolution to improve our representation – or model – of the world. To do so, we investigated the role of language in cultural evolution from a reinforcement learning perspective that proposes that adaptative behavior is based on learning from rewards and punishments. Using a combination of experiments, computational models, and large language models, we aimed to uncover the processes through which language fuels cultural evolution. We implemented a sequential decision-making task, requiring a mental model of the task structure within an online transmission chain design (n = 1000, 10 generations). Trough an evolutionary selection algorithm, best performing participant were sampled and provided written advice about their model of the task for the next generation. Consistent with the idea that language is important for cultural evolution, we observe an increase in performance and model knowledge over generations. Analysis using large-language models reveal an intergeneration improvement in the model knowledge communicated via written advice. Overall, these results suggest that language allows CE to grow better representations of the world by successive combination and refinement of individual world models.


**Speaker's social media:**

Twitter: @BlubluDoScience

Underline digital video library

AAAI/EAAI Patrick Henry Winston Outstanding Educator Award: T(w)eaching AI in the Age of LLMs

Propositional Interpretability in Humans and AI Systems

Can AI Benefit Humanity?

Can Large Language Models Reason about Spatial Information?

AI, Agents and Applications

Predicting Career Transitions and Estimating Wage Disparities Using Foundation Models

tagE: Enabling an Embodied Agent to Understand Human Instructions

The Vision Thing: Finding and Pursuing your Research Passion

Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users

LIVE - Humans can learn and culturally preserve inconceivable strategies discovered by intelligent machines

The Moral of the Story - Investigating the co-evolution of storytelling and Human Cooperation via a survey of moral attitudes to Indo-European folktales

LIVE - Language allows cultural evolution to improve world models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Underline digital video library

AAAI/EAAI Patrick Henry Winston Outstanding Educator Award: T(w)eaching AI in the Age of LLMs

Propositional Interpretability in Humans and AI Systems

Can AI Benefit Humanity?

Can Large Language Models Reason about Spatial Information?

AI, Agents and Applications

Predicting Career Transitions and Estimating Wage Disparities Using Foundation Models

tagE: Enabling an Embodied Agent to Understand Human Instructions​

The Vision Thing: Finding and Pursuing your Research Passion

Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users

LIVE - Humans can learn and culturally preserve inconceivable strategies discovered by intelligent machines

The Moral of the Story - Investigating the co-evolution of storytelling and Human Cooperation via a survey of moral attitudes to Indo-European folktales

LIVE - Language allows cultural evolution to improve world models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

tagE: Enabling an Embodied Agent to Understand Human Instructions