One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

Researchers in social science and psychology have recently proposed using large language models (LLMs) as replacements for humans in behavioral research. In addition to arguments about whether LLMs accurately capture population-level patterns, this has raised questions about whether LLMs capture human-like conceptual diversity. Separately, it is debated whether post-training alignment (RLHF or RLAIF) affects models' internal diversity. Inspired by human studies, we use a new way of measuring the conceptual diversity of synthetically-generated LLM "populations" by relating the internal variability of simulated individuals to the population-level variability. We use this approach to evaluate non-aligned and aligned LLMs on two domains with rich human behavioral data. While no model reaches human-like diversity, aligned models generally display less diversity than their instruction fine-tuned counterparts. Our findings highlight potential trade-offs between increasing models' value alignment and decreasing the diversity of their conceptual representations.

Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models

The ability to build and leverage world models is essential for a general-purpose AI agent. Testing such capabilities is hard, in part because the building blocks of world models are ill-defined. We present Elements of World Knowledge (EWOK), a framework for evaluating world modeling in language models by testing their ability to use knowledge of a concept to match a target text with a plausible/implausible context. EWOK targets specific concepts from multiple knowledge domains known to be vital for world modeling in humans. Domains range from social interactions (help/hinder) to spatial relations (left/right). Both, contexts and targets are minimal pairs. Objects, agents, and locations in the items can be flexibly filled in enabling easy generation of multiple controlled datasets. We then introduce EWOK-CORE-1.0, a dataset of 4,374 items covering 11 world knowledge domains. We evaluate 20 openweights large language models (1.3B--70B parameters) across a battery of evaluation paradigms along with a human norming study comprising 12,480 measurements. The overall performance of all tested models is worse than human performance, with results varying drastically across domains. These data highlight simple cases where even large models fail and present rich avenues for targeted research on LLM world modeling capabilities.

Auxiliary task demands mask the capabilities of smaller language models

Developmental psychologists have argued about when cognitive capacities such as language understanding or theory of mind emerge. These debates often hinge on the concept of "task demands" -- the auxiliary challenges associated with performing a particular evaluation -- that may mask the child's underlying ability. The same issues arise when measuring the capacities of language models (LMs): performance on a task is a function of the model's underlying competence, combined with the model's ability to interpret and perform the task given its available resources. Here, we show that for analogical reasoning, reflective reasoning, word prediction, and grammaticality judgments, evaluation methods with greater task demands yield lower performance than evaluations with reduced demands. This "demand gap" is most pronounced for models with fewer parameters and less training data. Our results illustrate that LM performance should not be interpreted as a direct indication of intelligence (or lack thereof), but as a reflection of capacities seen through the lens of researchers' design choices.

Language models align with human judgments on key grammatical constructions

Do Large Language Models (LLMs) make human-like linguistic generalizations? Dentella et al. (2023; "DGL") prompt several LLMs ("Is the following sentence grammatically correct in English?") to elicit grammaticality judgments of 80 English sentences, concluding that LLMs demonstrate a "yes-response bias" and a "failure to distinguish grammatical from ungrammatical sentences". We re-evaluate LLM performance using well-established practices and find that DGL's data in fact provide evidence for just how well LLMs capture human behaviors. Models not only achieve high accuracy overall, but also capture fine-grained variation in human linguistic judgments.

Prompt-based methods may underestimate large language models' linguistic generalizations

Prompting is now a dominant method for evaluating the linguistic knowledge of large language models (LLMs). While other methods directly read out models' probability distributions over strings, prompting requires models to access this internal information by processing linguistic input, thereby implicitly testing a new type of emergent ability: metalinguistic judgment. In this study, we compare metalinguistic prompting and direct probability measurements as ways of measuring models' knowledge of English. Broadly, we find that LLMs' metalinguistic judgments are inferior to quantities directly derived from representations. Furthermore, consistency gets worse as the prompt diverges from direct measurements of next-word probabilities. Our findings suggest that negative results relying on metalinguistic prompts cannot be taken as conclusive evidence that an LLM lacks a particular linguistic competence. Our results also highlight the lost value with the move to closed APIs where access to probability distributions is limited.

Expectations over Unspoken Alternatives Predict Pragmatic Inferences

Scalar inferences (SI) are a signature example of how humans interpret language based on unspoken alternatives. While empirical studies have demonstrated that human SI rates are highly variable -- both within instances of a single scale, and across different scales -- there have been few proposals that quantitatively explain both cross- and within-scale variation. Furthermore, while it is generally assumed that SIs arise through reasoning about unspoken alternatives, it remains debated whether humans reason about alternatives as linguistic forms, or at the level of concepts. Here, we test a shared mechanism explaining SI rates within and across scales: context-driven expectations about the unspoken alternatives. Using neural language models to approximate human predictive distributions, we find that SI rates are captured by the expectedness of the strong scalemate as an alternative. Crucially, however, expectedness robustly predicts cross-scale variation only under a meaning-based view of alternatives. Our results suggest that pragmatic inferences arise from context-driven expectations over alternatives, and these expectations operate at the level of concepts.

An AI Dungeon Master's Guide: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons

We propose a novel task, G4C (Goal-driven Guidance Generation in Grounded Communication), for studying goal-driven and grounded natural language interactions. Specifically, we choose Dungeons and Dragons (D&D) -- a role-playing game consisting of multiple player characters and a Dungeon Master (DM) who collaborate to achieve a set of goals that are beneficial to the players -- as a testbed for this task. Here, each of the player characters is a student, with their own personas and abilities, and the DM is the teacher, an arbitrator of the rules of the world and responsible for assisting and guiding the students towards a global goal. We propose a theory-of-mind-inspired methodology for training such a DM with reinforcement learning (RL), where a DM: (1) learns to predict how the players will react to its utterances using a dataset of D&D dialogue transcripts; and (2) uses this prediction as a reward function providing feedback on how effective these utterances are at guiding the players towards a goal. Human and automated evaluations show that a DM trained with RL to generate guidance by incorporating a theory-of-mind of the players significantly improves the players' ability to achieve goals grounded in their shared world.

A fine-grained comparison of pragmatic language understanding in humans and language models

Pragmatics is an essential part of communication, but it remains unclear what mechanisms underlie human pragmatic communication and whether NLP systems capture pragmatic language understanding. To investigate both these questions, we perform a fine-grained comparison of language models and humans on seven pragmatic phenomena, using zero-shot prompting on an expert-curated set of English materials. We ask whether models (1) select pragmatic interpretations of speaker utterances, (2) make similar error patterns as humans, and (3) use similar linguistic cues as humans to solve the tasks. We find that the largest models achieve high accuracy and match human error patterns: within incorrect responses, models favor the literal interpretation of an utterance over heuristic-based distractors. We also find evidence that models and humans are sensitive to similar linguistic cues. Our results suggest that even paradigmatic pragmatic phenomena may be solved without explicit representations of other agents' mental states, and that artificial models can be used to gain mechanistic insights into human pragmatic processing.

Pragmatics in Grounded Language Learning: Phenomena, Tasks, and Modeling Approaches

People rely heavily on context to enrich meaning beyond what is literally said, enabling concise but effective communication. To interact successfully and naturally with people, user-facing artificial intelligence systems will require similar skills in pragmatics: relying on various types of context -- from shared linguistic goals and conventions, to the visual and embodied world -- to use language effectively. We survey existing grounded settings and pragmatic modeling approaches and analyze how the task goals, environmental contexts, and communicative affordances in each work enrich linguistic meaning. We present recommendations for future grounded task design to naturally elicit pragmatic phenomena, and suggest directions that focus on a broader range of communicative contexts and affordances.

Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models

Prior work has shown that structural supervision helps English language models learn generalizations about syntactic phenomena such as subject-verb agreement. However, it remains unclear if such an inductive bias would also improve language models' ability to learn grammatical dependencies in typologically different languages. Here we investigate this question in Mandarin Chinese, which has a logographic, largely syllable-based writing system; different word order; and sparser morphology than English. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and Transformer-parameterized generative parsing models on two Mandarin Chinese datasets of different sizes. We evaluate the models' ability to learn different aspects of Mandarin grammar that assess syntactic and semantic relationships. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings, suggesting that the benefits of hierarchical inductive biases in acquiring dependency relationships may extend beyond English.