This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.

This paper systematically evaluates the consistency of popular causal discovery benchmarks against real-world scientific literature, revealing significant variability in their accuracy.

The paper introduces LLUMI, an open-source framework that improves LLM writing assistance for mental health support using community feedback, demonstrating comparable performance to proprietary models…

The paper proposes Test-Time Training for Supervised Causal Learning (TTT-SCL), a novel framework that dynamically generates training data aligned with specific test instances to significantly improve…

The paper theoretically explains that optimizing LLMs solely on outcomes leads to brittle reasoning (Reward-Induced Manifold Collapse) by favoring low-complexity shortcuts, and proposes process-based…

The paper compares verbalized feature attributions and self-generated rationales for explaining model behavior, finding that the format and granularity of the explanation significantly affect its abil…

The paper introduces CORE, a contrastive evidence organization method, which significantly improves the accuracy of LLM-based predictions of gene expression changes following cellular perturbations by…

The paper proposes 'Think Fast, Talk Smart,' a pipeline that separates deterministic data analysis from LLM generation, showing that offloading recurring, structured tasks to code significantly improv…

The paper introduces MIRA, a bilingual benchmark that reveals that LLMs tend to dilute or omit critical medical information when responding to prompts from users with low health literacy, a pattern te…

The paper introduces Factual Density (FD*), a novel retrieval signal that measures the proportion of verified facts, demonstrating that optimizing RAG retrieval based on this density significantly imp…

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

The paper introduces FRANZ, a communicative audit framework, to evaluate how LLMs frame responses to subjective questions, finding that LLMs exhibit statistically significant and coupled differences i…

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

The paper introduces AMNESIA, the first large-scale, open-source benchmark for medical unlearning, demonstrating that current unlearning methods struggle to separate individual patient data from share…

The paper proposes Shapley-based input uncertainty Quantification (ShaQ), a novel framework that uses Shapley values to precisely attribute input-induced uncertainty to specific spans of text, providi…

The paper introduces novel compatibility and incompatibility scores to evaluate collections of bivariate causal statements, providing a way to assess causal claims when ground truth is unavailable.

This paper proposes a domain-specialized large language model, PoetryQwen, for precise translation and emotional understanding of classical poetry.

The paper proposes graph-coupled causal Bayesian optimization, a method that improves efficiency by sharing information across related interventions through a shared set of causal parameters.

The paper investigates how language models perform entity tracking across state changes and finds that LMs use a non-incremental, parallel aggregation strategy rather than maintaining a true internal…