Category
4,637 papers
An LLM-based pipeline to automatically annotate longitudinal information in radiology reports is proposed, which outperforms existing annotation solutions, achieving 11.3\% and 5.3\% higher F1-scores for longitudinal information detection and disease tracking, respectively.
This work proposes CORE-T, a scalable, training-free framework that enriches tables with LLM-generated purpose metadata and pre-computes a lightweight table-compatibility cache, and uses 1.20x fewer total selection tokens than LLM-intensive baselines.
EvoCtx dynamically decides whether the next reasoning transition should cross the current evidence boundary through retrieval or refine the reasoning state within the existing context, and strategically alternates between boundary expansion and intra-boundary trajectory refinement.
It is suggested that CoT prompting activates specific latent features to trigger reasoning, and that targeted intervention on these features offers an alternative pathway to elicit efficient reasoning behavior without explicit CoT prompting.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces KinshipQA, a benchmark designed to probe large language models' ability to perform multi-hop reasoning through reasoning over kinship relations, and demonstrates that KinshipQA yields a wide spread of outcomes and exposes systematic differences in multi-hop reasoning across models and cultural settings.
This paper introduces a simple two-hop question answering setting, where answering a question requires making inferences over two multilingual documents, and finds that language models are more sensitive to language variation in answer-span documents than in those providing bridging information, despite the equal importance of both documents for answering a question.
AdaFuse is an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation that establishes a synergistic interaction between adaptive ensembling and test-time scaling, where ensemble decisions guide targeted exploration, and the resulting diversity in turn strengthens ensemble quality.
EpiQAL provides fine-grained diagnostic signals for evidence-grounding, inferential reasoning, and conclusion reconstruction for epidemiological question answering over research literature, comprising three subsets built from open-access articles across diverse diseases.
DIP is proposed, a context-optimization algorithm based on average verified confidence that dynamically ranks and inserts in-context examples during generation, rather than providing all examples up front.
Experiments show that EASD consistently improves accuracy over standard SD and reward-guided variants while maintaining comparable inference efficiency, suggesting that speculative decoding can serve not only as an acceleration method but also as an effective mechanism for improving reasoning quality.
We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective wisdom of multiple models with diverse strengths. LLM-PeerReview is built on a novel, peer-review-inspired framework that offers a transparent and interpretable mechanism, while remaining fully unsupervised for flexible adaptability and generalization. Specifically, it operates in three stages: For scoring, we use the emerging LLM-as-a-Judge technique to evaluate each response by reusing multiple LLMs at hand; For reasoning, we can apply a straightforward averaging strategy or a principled graphical model-based truth inference algorithm to aggregate multiple scores to produce a final score for each response; Finally, the highest-scoring response is selected as the best ensemble output. LLM-PeerReview is conceptually simple and empirically powerful. Our results across four datasets show that the two variants of the proposed approach outperform the advanced model Smoothie-Global by 6.9% and 7.3% points, cross diverse task types including factual recall QA, math reasoning, and instruction following. Notably, we also establish a carefully curated benchmark suite for LLM Ensemble, integrating 12 methods across four classic datasets and three task families, all evaluated under a rigorous and consistent protocol. We hope this repository will help researchers reproduce the LLM Ensemble baselines.
SGM is extensible, and its combined defenses, denoted as SGM*, integrate with existing detoxification methods for stronger safety performance, providing an interpretable, low-cost solution for toxicity-controlled multimodal generation.
Machine Intelligence
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
