The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…

The paper introduces AMix-2, a novel protein-text foundation model that unifies protein understanding and sequence design by embedding both modalities in a shared token space, achieving state-of-the-a…

The paper introduces FormInv, a measurement protocol that reveals significant semantic inconsistencies in existing mathematical reasoning benchmarks, showing that standard accuracy metrics fail to cap…

HypothesisMed introduces an inference-time pipeline for biomedical question answering that improves model reliability and structured output generation by fusing multiple model outputs and diagnosing t…

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.

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…

FuzzPilot is a controller for AFL++ that validates candidate mutation recipes by running short micro-campaigns, demonstrating a mechanism to manage fuzzing plateaus, though initial results on a satura…

This paper investigates whether the gains from using a Popperian falsificationist prompt skill in large language models are due to the skill's content or its structure.

This paper investigates whether the gains from using a Popperian falsificationist prompt skill in large language models are due to the skill's content or its structure.

The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.

The paper introduces a history-dependent bias to generative protein emulators, significantly improving the exploration of rare and diverse protein states compared to standard emulators.

The paper demonstrates that using raw source text for fine-tuning LLMs on vulnerability detection causes high false-positive rates by memorizing surface-level syntax, a problem mitigated by using Abst…

The paper introduces Ryze, an automated system that synthesizes evidence-enriched Question-Answering (QA) pairs from raw biomedical papers, resulting in a specialized VLM (BioVLM-8B) that significantl…

DeSQ is a novel, KB-agnostic framework that improves Knowledge Base Question Answering by decomposing complex questions into atomic constraints and generating structured SPARQL queries, achieving supe…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper introduces BioRefusalAudit, a method that audits the structural soundness of language model biosecurity refusals, finding that refusal behavior is highly unstable, often collapsing under min…

The paper audits the structural soundness of LLM biosecurity refusals, finding that refusal behavior is highly unstable, often collapsing under minor prompt changes, and may track legal salience rathe…

The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…