Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses that are unfaithful or hallucinated. This difficulty increases for contexts that are long or contain distracting information, which can divert LLMs from fully capturing essential evidence. To address this issue, many works use prompting to help LLMs utilize contextual information more faithfully. For instance, iterative prompting highlights key information in two steps that first ask the LLM to identify important pieces of context and then derive answers accordingly. However, prompting methods are constrained to highlighting key information implicitly in token space, which is often insufficient to fully steer the model's attention. To improve model faithfulness more reliably, we propose AutoPASTA, a method that automatically identifies key contextual information and explicitly highlights it by steering an LLM's attention scores. Like prompting, AutoPASTA is applied at inference time and does not require changing any model parameters. Our experiments on open-book QA demonstrate that AutoPASTA effectively enables models to grasp essential contextual information, leading to substantially improved model faithfulness and performance, e.g., an average improvement of 7.95% for LLAMA3-70B-Instruct. Code will be publicly available at https://github.com/QingruZhang/AutoPASTA .

BRANFORD, Conn., Sept. 13, 2016 -- BioXcel, a privately held biopharmaceutical company based in Connecticut, today announced that the U. S. Food and Drug Administration (FDA) has granted Orphan Drug Designation to BXCL101 for the treatment of Neurofibromatosis Type 2 (NF2), an orphan disease with significant unmet medical need. BXCL101 is the first and only systemic therapy being developed to eliminate existing lesions and prevent the formation of new lesions by targeting the molecular mechanism of NF2 pathophysiology. BXCL101 is a proprietary version of an approved drug, bortezomib, adapted for chronic use in NF2 patients with both a novel dosing regimen and delivery approach. NF2 is a rare disease associated with neurologic and ophthalmologic abnormalities caused by benign tumors of the brain, spinal cord and peripheral nerves. BXCL101 is the first drug candidate discovered using BioXcel's R&D Platform, to be granted orphan drug status by the FDA.

The softassign quadratic assignment algorithm has recently emerged as an effective strategy for a variety of optimization problems in pattern recognition and combinatorial optimization. While the effectiveness of the algorithm was demonstrated in thousands of simulations, there was no known proof of convergence. Here, we provide a proof of convergence for the most general form of the algorithm.

The softassign quadratic assignment algorithm has recently emerged as an effective strategy for a variety of optimization problems in pattern recognition and combinatorial optimization. While the effectiveness of the algorithm was demonstrated in thousands of simulations, there was no known proof of convergence. Here, we provide a proof of convergence for the most general form of the algorithm.