The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. This study focused on evaluating and enhancing the clinical capabilities of LLMs in specific domains, using osteoarthritis (OA) management as a case study. A domain specific benchmark framework was developed, which evaluate LLMs across a spectrum from domain-specific knowledge to clinical applications in real-world clinical scenarios. DocOA, a specialized LLM tailored for OA management that integrates retrieval-augmented generation (RAG) and instruction prompts, was developed. The study compared the performance of GPT-3.5, GPT-4, and a specialized assistant, DocOA, using objective and human evaluations. Results showed that general LLMs like GPT-3.5 and GPT-4 were less effective in the specialized domain of OA management, particularly in providing personalized treatment recommendations. However, DocOA showed significant improvements. This study introduces a novel benchmark framework which assesses the domain-specific abilities of LLMs in multiple aspects, highlights the limitations of generalized LLMs in clinical contexts, and demonstrates the potential of tailored approaches for developing domain-specific medical LLMs.

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the form of backdoor attacks, wherein the model will output unintended malicious content under specific backdoor-triggered conditions during inference. Traditional methods for launching backdoor attacks involve either contaminating the training dataset with backdoored instances or directly manipulating the model parameters during deployment. However, these approaches are not practical for commercial LLMs that typically operate via API access. In this paper, we propose BadChain, the first backdoor attack against LLMs employing COT prompting, which does not require access to the training dataset or model parameters and imposes low computational overhead. BadChain leverages the inherent reasoning capabilities of LLMs by inserting a backdoor reasoning step into the sequence of reasoning steps of the model output, thereby altering the final response when a backdoor trigger exists in the query prompt. Empirically, we show the effectiveness of BadChain for two COT strategies across four LLMs (Llama2, GPT-3.5, PaLM2, and GPT-4) and six complex benchmark tasks encompassing arithmetic, commonsense, and symbolic reasoning. Moreover, we show that LLMs endowed with stronger reasoning capabilities exhibit higher susceptibility to BadChain, exemplified by a high average attack success rate of 97.0% across the six benchmark tasks on GPT-4. Finally, we propose two defenses based on shuffling and demonstrate their overall ineffectiveness against BadChain. Therefore, BadChain remains a severe threat to LLMs, underscoring the urgency for the development of robust and effective future defenses.

Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence. Compared with general information extraction (IE), OpenIE poses more challenges for the IE models, {especially when multiple complicated triplets exist in a sentence. To extract these complicated triplets more effectively, in this paper we propose a novel generative OpenIE model, namely \emph{DualOIE}, which achieves a dual task at the same time as extracting some triplets from the sentence, i.e., converting the triplets into the sentence.} Such dual task encourages the model to correctly recognize the structure of the given sentence and thus is helpful to extract all potential triplets from the sentence. Specifically, DualOIE extracts the triplets in two steps: 1) first extracting a sequence of all potential predicates, 2) then using the predicate sequence as a prompt to induce the generation of triplets. Our experiments on two benchmarks and our dataset constructed from Meituan demonstrate that DualOIE achieves the best performance among the state-of-the-art baselines. Furthermore, the online A/B test on Meituan platform shows that 0.93\% improvement of QV-CTR and 0.56\% improvement of UV-CTR have been obtained when the triplets extracted by DualOIE were leveraged in Meituan's search system.

We introduce PhotoBot, a framework for automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer. We propose to communicate photography suggestions to the user via a reference picture that is retrieved from a curated gallery. We exploit a visual language model (VLM) and an object detector to characterize reference pictures via textual descriptions and use a large language model (LLM) to retrieve relevant reference pictures based on a user's language query through text-based reasoning. To correspond the reference picture and the observed scene, we exploit pre-trained features from a vision transformer capable of capturing semantic similarity across significantly varying images. Using these features, we compute pose adjustments for an RGB-D camera by solving a Perspective-n-Point (PnP) problem. We demonstrate our approach on a real-world manipulator equipped with a wrist camera. Our user studies show that photos taken by PhotoBot are often more aesthetically pleasing than those taken by users themselves, as measured by human feedback.

This study is dedicated to evaluating the capabilities of advanced large language models (LLMs) such as GPT-3.5-Turbo, GPT-4, and GPT-4-Turbo in the extraction of structured information from scientific documents within the field of materials science. We introduce a novel methodology for the comparative analysis of intricate material expressions, emphasising the standardisation of chemical formulas to tackle the complexities inherent in materials science information assessment. To this end, we primarily focus on two critical tasks of information extraction: (i) a named entity recognition (NER) of studied materials and physical properties and (ii) a relation extraction (RE) between these entities. The performance of LLMs in executing these tasks is benchmarked against traditional models based on the BERT architecture and rule-based approaches. For NER, LLMs fail to outperform the baseline with zero-shot prompting and exhibit only limited improvement with few-shot prompting. However, for RE, a GPT-3.5-Turbo fine-tuned with the appropriate strategy outperforms all models, including the baseline. Without any fine-tuning, GPT-4 and GPT-4-Turbo display remarkable reasoning and relationship extraction capabilities after being provided with merely a couple of examples, surpassing the baseline. Overall, the results suggest that although LLMs demonstrate relevant reasoning skills in connecting concepts, for tasks requiring extracting complex domain-specific entities like materials, specialised models are currently a better choice.

PubTator 3.0 (https://www.ncbi.nlm.nih.gov/research/pubtator3/) is a biomedical literature resource using state-of-the-art AI techniques to offer semantic and relation searches for key concepts like proteins, genetic variants, diseases, and chemicals. It currently provides over one billion entity and relation annotations across approximately 36 million PubMed abstracts and 6 million full-text articles from the PMC open access subset, updated weekly. PubTator 3.0's online interface and API utilize these precomputed entity relations and synonyms to provide advanced search capabilities and enable large-scale analyses, streamlining many complex information needs. We showcase the retrieval quality of PubTator 3.0 using a series of entity pair queries, demonstrating that PubTator 3.0 retrieves a greater number of articles than either PubMed or Google Scholar, with higher precision in the top 20 results. We further show that integrating ChatGPT (GPT-4) with PubTator APIs dramatically improves the factuality and verifiability of its responses. In summary, PubTator 3.0 offers a comprehensive set of features and tools that allow researchers to navigate the ever-expanding wealth of biomedical literature, expediting research and unlocking valuable insights for scientific discovery.

We present the Radiation Oncology NLP Database (ROND), the first dedicated Natural Language Processing (NLP) dataset for radiation oncology, an important medical specialty that has received limited attention from the NLP community in the past. With the advent of Artificial General Intelligence (AGI), there is an increasing need for specialized datasets and benchmarks to facilitate research and development. ROND is specifically designed to address this gap in the domain of radiation oncology, a field that offers many opportunities for NLP exploration. It encompasses various NLP tasks including Logic Reasoning, Text Classification, Named Entity Recognition (NER), Question Answering (QA), Text Summarization, and Patient-Clinician Conversations, each with a distinct focus on radiation oncology concepts and application cases. In addition, we have developed an instruction-tuning dataset consisting of over 20k instruction pairs (based on ROND) and trained a large language model, CancerChat. This serves to demonstrate the potential of instruction-tuning large language models within a highly-specialized medical domain. The evaluation results in this study could serve as baseline results for future research. ROND aims to stimulate advancements in radiation oncology and clinical NLP by offering a platform for testing and improving algorithms and models in a domain-specific context. The ROND dataset is a joint effort of multiple U.S. health institutions. The data is available at https://github.com/zl-liu/Radiation-Oncology-NLP-Database.

In recent years, generative AI has undergone major advancements, demonstrating significant promise in augmenting human productivity. Notably, large language models (LLM), with ChatGPT-4 as an example, have drawn considerable attention. Numerous articles have examined the impact of LLM-based tools on human productivity in lab settings and designed tasks or in observational studies. Despite recent advances, field experiments applying LLM-based tools in realistic settings are limited. This paper presents the findings of a field randomized controlled trial assessing the effectiveness of LLM-based tools in providing unmonitored support services for information retrieval.

In this study, we investigate the enhancement of the GPT Neo 125M performance in Community Question Answering (CQA) with a focus on programming, through the integration of Reinforcement Learning from Human Feedback (RLHF) and the utilization of scores from Stack Overflow. Two distinct reward model training strategies are employed for fine-tuning with Proximal Policy Optimization (PPO). Notably, the improvements in performance achieved through this method are comparable to those of GPT Neo 2.7B parameter variant. Additionally, an auxiliary scoring mechanism is introduced, which demonstrates the limitations of conventional linguistic metrics in evaluating responses in the programming domain. Through accurate analysis, this paper looks at the divergence between traditional linguistic metrics and our human-preferences-based reward model, underscoring the imperative for domain-specific evaluation methods. By elucidating the complexities involved in applying RLHF to programming CQA and accentuating the significance of context-aware evaluation, this study contributes to the ongoing efforts in refining Large Language Models through focused human feedback.

Large Language Models (LLMs) are vulnerable to `Jailbreaking' prompts, a type of attack that can coax these models into generating harmful and illegal content. In this paper, we show that pruning up to 20% of LLM parameters markedly increases their resistance to such attacks without additional training and without sacrificing their performance in standard benchmarks. Intriguingly, we discovered that the enhanced safety observed post-pruning correlates to the initial safety training level of the model, hinting that the effect of pruning could be more general and may hold for other LLM behaviors beyond safety. Additionally, we introduce a curated dataset of 225 harmful tasks across five categories, inserted into ten different Jailbreaking prompts, showing that pruning aids LLMs in concentrating attention on task-relevant tokens in jailbreaking prompts. Lastly, our experiments reveal that the prominent chat models, such as LLaMA-2 Chat, Vicuna, and Mistral Instruct exhibit high susceptibility to jailbreaking attacks, with some categories achieving nearly 70-100% success rate. These insights underline the potential of pruning as a generalizable approach for improving LLM safety, reliability, and potentially other desired behaviors.