There are two common ways in which developers are incorporating proprietary and domain-specific data when building applications of Large Language Models (LLMs): Retrieval-Augmented Generation (RAG) and Fine-Tuning. RAG augments the prompt with the external data, while fine-Tuning incorporates the additional knowledge into the model itself. However, the pros and cons of both approaches are not well understood. In this paper, we propose a pipeline for fine-tuning and RAG, and present the tradeoffs of both for multiple popular LLMs, including Llama2-13B, GPT-3.5, and GPT-4. Our pipeline consists of multiple stages, including extracting information from PDFs, generating questions and answers, using them for fine-tuning, and leveraging GPT-4 for evaluating the results. We propose metrics to assess the performance of different stages of the RAG and fine-Tuning pipeline. We conduct an in-depth study on an agricultural dataset. Agriculture as an industry has not seen much penetration of AI, and we study a potentially disruptive application - what if we could provide location-specific insights to a farmer? Our results show the effectiveness of our dataset generation pipeline in capturing geographic-specific knowledge, and the quantitative and qualitative benefits of RAG and fine-tuning. We see an accuracy increase of over 6 p.p. when fine-tuning the model and this is cumulative with RAG, which increases accuracy by 5 p.p. further. In one particular experiment, we also demonstrate that the fine-tuned model leverages information from across geographies to answer specific questions, increasing answer similarity from 47% to 72%. Overall, the results point to how systems built using LLMs can be adapted to respond and incorporate knowledge across a dimension that is critical for a specific industry, paving the way for further applications of LLMs in other industrial domains.

We propose Compact and Swift Segmenting 3D Gaussians(CoSSegGaussians), a method for compact 3D-consistent scene segmentation at fast rendering speed with only RGB images input. Previous NeRF-based segmentation methods have relied on time-consuming neural scene optimization. While recent 3D Gaussian Splatting has notably improved speed, existing Gaussian-based segmentation methods struggle to produce compact masks, especially in zero-shot segmentation. This issue probably stems from their straightforward assignment of learnable parameters to each Gaussian, resulting in a lack of robustness against cross-view inconsistent 2D machine-generated labels. Our method aims to address this problem by employing Dual Feature Fusion Network as Gaussians' segmentation field. Specifically, we first optimize 3D Gaussians under RGB supervision. After Gaussian Locating, DINO features extracted from images are applied through explicit unprojection, which are further incorporated with spatial features from the efficient point cloud processing network. Feature aggregation is utilized to fuse them in a global-to-local strategy for compact segmentation features. Experimental results show that our model outperforms baselines on both semantic and panoptic zero-shot segmentation task, meanwhile consumes less than 10% inference time compared to NeRF-based methods. Code and more results will be available at https://David-Dou.github.io/CoSSegGaussians

The success of drug discovery and development relies on the precise prediction of molecular activities and properties. While in silico molecular property prediction has shown remarkable potential, its use has been limited so far to assays for which large amounts of data are available. In this study, we use a fine-tuned large language model to integrate biological assays based on their textual information, coupled with Barlow Twins, a Siamese neural network using a novel self-supervised learning approach. This architecture uses both assay information and molecular fingerprints to extract the true molecular information. TwinBooster enables the prediction of properties of unseen bioassays and molecules by providing state-of-the-art zero-shot learning tasks. Remarkably, our artificial intelligence pipeline shows excellent performance on the FS-Mol benchmark. This breakthrough demonstrates the application of deep learning to critical property prediction tasks where data is typically scarce. By accelerating the early identification of active molecules in drug discovery and development, this method has the potential to help streamline the identification of novel therapeutics.

RAISE, an enhancement exhibit high levels of performance in isolated of the ReAct framework, incorporates a tasks, creating an agent that can sustain coherent, dual-component memory system, mirroring context-aware, and purpose-driven conversations human short-term and long-term memory, remains an intricate endeavor. The need for to maintain context and continuity a more sophisticated framework that leverages the in conversations. It entails a comprehensive strengths of LLMs while addressing their limitations agent construction scenario, including in conversational settings has become increasingly phases like Conversation Selection, apparent. Scene Extraction, CoT Completion, and In response to this need, we introduce the Scene Augmentation, leading to the LLMs RAISE (Reasoning and Acting through Scratchpad Training phase. This approach appears to and Examples) architecture. RAISE represents enhance agent controllability and adaptability a refined enhancement of the existing Rein complex, multi-turn dialogues. Act(Yao et al., 2023) framework, specifically designed Our preliminary evaluations in a real estate to augment the capabilities of conversational sales context suggest that RAISE has agents. This paper presents a detailed exploration some advantages over traditional agents, of RAISE, highlighting its unique components indicating its potential for broader applications.

Recent advances in large language models (LLMs) have led to the development of various evaluation benchmarks. These benchmarks typically rely on a single instruction template for evaluating all LLMs on a specific task. In this paper, we comprehensively analyze the brittleness of results obtained via single-prompt evaluations across 6.5M instances, involving 20 different LLMs and 39 tasks from 3 benchmarks. To improve robustness of the analysis, we propose to evaluate LLMs with a set of diverse prompts instead. We discuss tailored evaluation metrics for specific use cases (e.g., LLM developers vs. developers interested in a specific downstream task), ensuring a more reliable and meaningful assessment of LLM capabilities. We then implement these criteria and conduct evaluations of multiple models, providing insights into the true strengths and limitations of current LLMs.

Emergency and non-emergency response systems are essential services provided by local governments and critical to protecting lives, the environment, and property. The effective handling of (non-)emergency calls is critical for public safety and well-being. By reducing the burden through non-emergency callers, residents in critical need of assistance through 911 will receive a fast and effective response. Collaborating with the Department of Emergency Communications (DEC) in Nashville, we analyzed 11,796 non-emergency call recordings and developed Auto311, the first automated system to handle 311 non-emergency calls, which (1) effectively and dynamically predicts ongoing non-emergency incident types to generate tailored case reports during the call; (2) itemizes essential information from dialogue contexts to complete the generated reports; and (3) strategically structures system-caller dialogues with optimized confidence. We used real-world data to evaluate the system's effectiveness and deployability. The experimental results indicate that the system effectively predicts incident type with an average F-1 score of 92.54%. Moreover, the system successfully itemizes critical information from relevant contexts to complete reports, evincing a 0.93 average consistency score compared to the ground truth. Additionally, emulations demonstrate that the system effectively decreases conversation turns as the utterance size gets more extensive and categorizes the ongoing call with 94.49% mean accuracy.

We find the location of factual knowledge in large language models by exploring the residual stream and analyzing subvalues in vocabulary space. We find the reason why subvalues have human-interpretable concepts when projecting into vocabulary space. The before-softmax values of subvalues are added by an addition function, thus the probability of top tokens in vocabulary space will increase. Based on this, we find using log probability increase to compute the significance of layers and subvalues is better than probability increase, since the curve of log probability increase has a linear monotonically increasing shape. Moreover, we calculate the inner products to evaluate how much a feed-forward network (FFN) subvalue is activated by previous layers. Base on our methods, we find where factual knowledge is stored. Specifically, attention layers store "Paris is related to France". FFN layers store "Paris is a capital/city", activated by attention subvalues related to "capital". We leverage our method on Baevski-18, GPT2 medium, Llama-7B and Llama-13B. Overall, we provide a new method for understanding the mechanism of transformers. We will release our code on github.

Zero-shot voice conversion (VC) aims to transfer the source speaker timbre to arbitrary unseen target speaker timbre, while keeping the linguistic content unchanged. Although the voice of generated speech can be controlled by providing the speaker embedding of the target speaker, the speaker similarity still lags behind the ground truth recordings. In this paper, we propose SEF-VC, a speaker embedding free voice conversion model, which is designed to learn and incorporate speaker timbre from reference speech via a powerful position-agnostic cross-attention mechanism, and then reconstruct waveform from HuBERT semantic tokens in a non-autoregressive manner. The concise design of SEF-VC enhances its training stability and voice conversion performance. Objective and subjective evaluations demonstrate the superiority of SEF-VC to generate high-quality speech with better similarity to target reference than strong zero-shot VC baselines, even for very short reference speeches.

Creativity is core to being human. Generative artificial intelligence (GenAI) -- including ever more powerful large language models (LLMs) -- holds promise for humans to be more creative by offering new ideas, or less creative by anchoring on GenAI ideas. We study the causal impact of GenAI ideas on the production of a short story in an online experimental study where some writers could obtain story ideas from a GenAI platform. We find that access to GenAI ideas causes stories to be evaluated as more creative, better written, and more enjoyable, especially among less creative writers. However, GenAI-enabled stories are more similar to each other than stories by humans alone. These results point to an increase in individual creativity at the risk of losing collective novelty. This dynamic resembles a social dilemma: with GenAI, individual writers are better off, but collectively a narrower scope of novel content may be produced. Our results have implications for researchers, policy-makers and practitioners interested in bolstering creativity.

This work introduces self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding. Our approach capitalizes on the observation that recent infilling-capable code language models can self-infill: whereas infilling operations aim to fill in the middle based on a predefined prefix and suffix, self-infilling sequentially generates both such surrounding context and the infilled content. We utilize this capability to introduce novel interruption and looping mechanisms in conventional decoding, evolving it into a non-monotonic process. Interruptions allow for postponing the generation of specific code until a definitive suffix is established, enhancing control over the output. Meanwhile, the looping mechanism, which leverages the complementary nature of self-infilling and left-to-right decoding, can iteratively update and synchronize each piece of generation cyclically. Extensive experiments are conducted to demonstrate that our proposed decoding process is effective in enhancing both regularity and quality across several code generation benchmarks.