arXiv subjects

Thomas T. Hills

Publications and source records attributed to Thomas T. Hills.

3 recordsLinked to original sources

arXiv2026

EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts

Existing scientific relation extraction benchmarks mainly target domains such as computer science, where entities are tasks, methods, datasets, materials, or metrics. This leaves a gap in variable-oriented empirical fields such as psychology, where findings are expressed as relations among constructs, measurements, interventions, and outcomes. We introduce variable-centered empirical graph extraction, the task of mapping scientific abstracts to typed graphs whose nodes are normalized variables and whose edges represent empirical and hierarchical relations. To support this task, we construct EmpiriGraph-Psy, a benchmark of 210 psychology abstracts annotated by domain-trained annotators with normalized variables, concept hierarchies, empirical relation types, and validation states. We evaluate frontier and open-weight LLMs using both direct extraction and a staged graph-construction pipeline that separates variable extraction, normalization, hierarchy construction, evidence selection, relation extraction, and edge validation. The staged pipeline substantially outperforms direct extraction, with the best configuration achieving a macro-F1 of 0.74. Error analysis shows that moderation relations and concept hierarchies remain the most challenging cases, highlighting the difficulty of extracting higher-order empirical claims and implicit abstraction structure from scientific abstracts.

cs.IR↗

arXiv2025

Could you be wrong: Debiasing LLMs using a metacognitive prompt for improving human decision making

Identifying bias in LLMs is ongoing. Because they are still in development, what is true today may be false tomorrow. We therefore need general strategies for debiasing that will outlive current models. Strategies developed for debiasing human decision making offer one promising approach as they incorporate an LLM-style prompt intervention designed to bring latent knowledge into awareness during decision making. LLMs trained on vast amounts of information contain information about potential biases, counter-arguments, and contradictory evidence, but that information may only be brought to bear if prompted. Metacognitive prompts developed in the human decision making literature are designed to achieve this, and as I demonstrate here, they show promise with LLMs. The prompt I focus on here is "could you be wrong?" Following an LLM response, this prompt leads LLMs to produce additional information, including why they answered as they did, errors, biases, contradictory evidence, and alternatives, none of which were apparent in their initial response. Indeed, this metaknowledge often reveals that how LLMs and users interpret prompts are not aligned. Here I demonstrate this prompt using a set of questions taken from recent articles about LLM biases, including implicit discriminatory biases and failures of metacognition. "Could you be wrong" prompts the LLM to identify its own biases and produce cogent metacognitive reflection. I also present another example involving convincing but incomplete information, which is readily corrected by the metacognitive prompt. In sum, this work argues that human psychology offers a new avenue for prompt engineering, leveraging a long history of effective prompt-based improvements to human decision making.

cs.AI↗

arXiv2023

The Rising Entropy of English in the Attention Economy

We present evidence that the word entropy of American English has been rising steadily since around 1900, contrary to predictions from existing sociolinguistic theories. We also find differences in word entropy between media categories, with short-form media such as news and magazines having higher entropy than long-form media, and social media feeds having higher entropy still. To explain these results we develop an ecological model of the attention economy that combines ideas from Zipf's law and information foraging. In this model, media consumers maximize information utility rate taking into account the costs of information search, while media producers adapt to technologies that reduce search costs, driving them to generate higher entropy content in increasingly shorter formats.

econ.GN↗