Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation. To address these issues, we propose \textbf{RetroLLM}, a unified framework that integrates retrieval and generation into a single, cohesive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding. Moreover, to mitigate false pruning in the process of constrained evidence generation, we introduce (1) hierarchical FM-Index constraints, which generate corpus-constrained clues to identify a subset of relevant documents before evidence generation, reducing irrelevant decoding space; and (2) a forward-looking constrained decoding strategy, which considers the relevance of future sequences to improve evidence accuracy. Extensive experiments on five open-domain QA datasets demonstrate RetroLLM's superior performance across both in-domain and out-of-domain tasks. The code is available at \url{https://github.com/sunnynexus/RetroLLM}.

Incorporating external knowledge into dialogue generation (KIDG) is crucial for improving the correctness of response, where evidence fragments serve as knowledgeable snippets supporting the factual dialogue replies. However, introducing irrelevant content often adversely impacts reply quality and easily leads to hallucinated responses. Prior work on evidence retrieval and integration in dialogue systems falls short of fully leveraging existing evidence since the model fails to locate useful fragments accurately and overlooks hidden evidence labels within the KIDG dataset. To fully Unleash the potential of evidence, we propose a framework to effectively incorporate Evidence in knowledge-Intensive Dialogue Generation (u-EIDG). Specifically, we introduce an automatic evidence generation framework that harnesses the power of Large Language Models (LLMs) to mine reliable evidence veracity labels from unlabeled data. By utilizing these evidence labels, we train a reliable evidence indicator to effectively identify relevant evidence from retrieved passages. Furthermore, we propose an evidence-augmented generator with an evidence-focused attention mechanism, which allows the model to concentrate on evidenced segments. Experimental results on MultiDoc2Dial demonstrate the efficacy of evidential label augmentation and refined attention mechanisms in improving model performance. Further analysis confirms that the proposed method outperforms other baselines (+3~+5 points) regarding coherence and factual consistency.

Iterative Scopes, a pioneer in precision-medicine technologies for gastroenterology, announced that Shrujal Baxi, MD, MPH, has joined its leadership team as Chief Medical Officer. "Having a stellar scientific, medical, and regulatory affairs team is critical to Iterative Scopes' work, and we're very excited to have Dr. Baxi leading these groups," says Jonathan Ng, MBBS, founder and CEO of Iterative Scopes. "As a medical oncologist, Dr. Baxi has witnessed a transformation in oncology that has accelerated the public's understanding of cancer while also fueling precise management of the disease. Data has driven this innovation and knowledge generation, and I look forward to seeing her apply this expertise to our focus on individualized care for people with inflammatory bowel disease." Dr. Baxi specializes in real-world evidence generation, and throughout her career has been involved in multiple clinical trials.

Join us for Outsourcing-Pharma's upcoming editorial webinar, titled Real Use Cases for Artificial Intelligence: Where are we now? This discussion will feature expert insights from Sudip Parikh, PhD, senior vice president and managing director, Americas, DIA Global; Doug Peddicord, PhD, executive director, Association of Clinical Research Organizations (ACRO); and Thomas Clozel, MD, co-founder and CEO, Owkin . The Real Use Cases for Artificial Intelligence webinar is sponsored by: Acorn AI (a Medidata company); OM1; ICON plc; and Elligo Health Research . For more information and to register for FREE, please click HERE . The industry, across the drug development continuum, has so far this year announced myriad new partnerships, strategic alliances, product launches, and reports.