Hua-Dong Xiong

Hua-Dong Xiong, Li Ji-An, Robert C. Wilson et al.

Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a capability known as in-context learning (ICL). Prior work on synthetic tasks has shown that ICL can implement specific algorithms, demonstrating architectural competence, and mechanistic analyses have identified key circuits that support this behavior. However, because in-context computation -- regardless of its algorithmic form -- relies on transformations in high-dimensional representation space, it remains unclear how the geometry of that space shapes ICL effectiveness. Motivated by the neuroscience view of classification as the untangling of neural representations, we hypothesize that ICL depends on the successful online untangling of task-relevant representations. To test this idea, we study how LLMs classify in-context examples whose labels are defined by the model's own internal representations with known structure. We show that ICL performance correlates systematically with the representational structure of the underlying classification task and that successful ICL is accompanied by geometric reorganization that increases online separability. We further find that LLM behavior is well described by a prototype-like algorithm that integrates evidence while reshaping representations to support classification. These findings offer a geometric account of ICL in pretrained LLMs, establish representational geometry as a mechanistic constraint on ICL, and quantify the gap between what pretrained representations afford and what in-context learning can exploit.

Marcel Binz, Elif Akata, Abdullah Almaatouq et al.

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.

Hua-Dong Xiong, Li Ji-An, Jiaqi Huang et al.

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite having on the order of 100 billion neurons, both biological and artificial systems exhibit limitations in working memory. This raises a key question: why do large language models (LLMs) show such limitations, given that transformers have full access to prior context through attention? We find that although a two-layer transformer can be trained to solve working memory tasks perfectly, a diverse set of pretrained LLMs continues to show working memory limitations. Notably, LLMs reproduce interference signatures observed in humans: performance degrades with increasing memory load and is biased by recency and stimulus statistics. Across models, stronger working memory capacity correlates with broader competence on standard benchmarks, mirroring its link to general intelligence in humans. Yet despite substantial variability in working memory performance, LLMs surprisingly converge on a common computational mechanism. Rather than directly copying the relevant memory item from context, models encode multiple memory items in entangled representations, such that successful recall depends on interference control -- actively suppressing task-irrelevant content to isolate the target for readout. Moreover, a targeted intervention that suppresses stimulus content information improves performance, providing causal support for representational interference. Together, these findings identify representational interference as a core constraint on working memory in pretrained LLMs, suggesting that working-memory limits in biological and artificial systems may reflect a shared computational challenge: selecting task-relevant information under interference.

Zhanqi Zhang, Hua-Dong Xiong, Robert C. Wilson et al.

Modern large language models (LLMs) can find a needle in a haystack (locating a single relevant fact buried among hundreds of thousands of irrelevant tokens) with near-saturated accuracy, yet fail to retrieve the last few items in a short list. We call this failure the Position Curse. For instance, even in a two-line code snippet, Claude Opus 4.6 misidentifies the second-to-last line most of the time. To characterize this failure, we evaluated two complementary queries: given a position in a sequence (of letters or words), retrieve the corresponding item; and given an item, return its position. Each position is specified as a forward or backward offset from an anchor, either an endpoint of the list (its start or end) or another item in the list. Across both open-source and frontier closed-source models, backward retrieval substantially lags forward retrieval. To test whether this capability can be rescued by post-training, we constructed PosBench, a position-focused training dataset. LoRA fine-tuning improves both forward and backward retrieval and generalizes to a held-out code-understanding benchmark (PyIndex), yet absolute performance remains far from saturated. As LLM coding agents increasingly operate over large codebases where precise indexing becomes essential for code understanding and editing, position-based retrieval emerges as a key capability for future pretraining objectives and model design.

Hua-Dong Xiong

Large language models (LLMs) increasingly help people solve problems, from debugging code to repairing machinery. This process requires generating plausible hypotheses from partial descriptions, then updating them as more information arrives. Yet how LLMs perform this form of inference, and how close it is to optimal, remains unclear. We study this question in the number game, a controlled setting in which a learner infers the hypothesis supported by a few positive integers, such as $\{16, 8, 2, 64\}$: a rule like powers of 2 or an interval like numbers near 20. We measure the posterior over hypotheses using three complementary probes: posterior prediction, hypothesis evaluation, and hypothesis generation. We then compare LLM behavior with an optimal Bayesian model and human behavior, and test whether the same posterior is expressed across probes. LLMs are often well described by a two-parameter Bayesian fit, but with systematic offsets: by default they show a strong-sampling assumption that creates an implicit Occam's razor, favoring narrower hypotheses, while thinking mode shifts them toward greater prior reliance. We also find a robust evaluation--generation gap: LLMs select more correct hypotheses during hypothesis evaluation but generate simpler, more rule-like hypotheses. Finally, this Bayesian-with-bias pattern does not extrapolate. Models can behave as if they hold rule-like hypotheses over observed examples, yet generalize poorly to parts of the hypothesis domain not covered by those examples. Our results highlight a limitation of LLMs as general problem solvers, especially for scientific inference, where hypotheses must go beyond the data.

Marcel Binz, Elif Akata, Matthias Bethge et al. · princeton

Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational models, we currently do not have one model that captures the human mind in its entirety. A first step in this direction is to create a model that can predict human behavior in a wide range of settings. Here we introduce Centaur, a computational model that can predict and simulate human behavior in any experiment expressible in natural language. We derived Centaur by finetuning a state-of-the-art language model on a novel, large-scale data set called Psych-101. Psych-101 reaches an unprecedented scale, covering trial-by-trial data from over 60,000 participants performing over 10,000,000 choices in 160 experiments. Centaur not only captures the behavior of held-out participants better than existing cognitive models, but also generalizes to new cover stories, structural task modifications, and entirely new domains. Furthermore, we find that the model's internal representations become more aligned with human neural activity after finetuning. Taken together, our results demonstrate that it is possible to discover computational models that capture human behavior across a wide range of domains. We believe that such models provide tremendous potential for guiding the development of cognitive theories and present a case study to demonstrate this.

Hua-Dong Xiong, Xinyuan Yan, Ji-An Li et al.

Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence more effectively or seek information that could improve future decisions. We distinguish these responses by measuring action preference, thinking length, and reported confidence under matched uncertainty. Ten open-weight models completed matched horizon-style two-armed bandit trials in thinking and non-thinking modes. A cognitive model separated value-guided action and uncertainty-independent choice noise from two behavioral signatures of exploration: a UCB-like preference for the less-known arm and Thompson-like choice variability that increases with total uncertainty. On average, thinking strengthened value-guided action and reduced uncertainty-independent choice noise, without producing UCB-like exploration or strengthening Thompson-like exploration. Outside action, the information-imbalanced history condition, which also displayed more observations than the matched balanced condition, was associated with greater thinking length. Reported confidence became more sensitive to decision difficulty and more strongly associated with chosen task evidence. We interpret these thinking-length and reported-confidence patterns as consistent with metacognitive control and metacognitive monitoring, respectively, without establishing either process. Decoder sweeps, especially temperature, altered choice noise and thinking length but did not reproduce the joint cross-output pattern. In this controlled decision setting, thinking improved how models acted on current evidence, while neither measured signature supported a shift toward a more information-seeking policy.