This paper's primary goal is to provoke thoughtful discussion about the relationship between bias and fundamental properties of large language models. We do this by seeking to convince the reader that harmful biases are an inevitable consequence arising from the design of any large language model as LLMs are currently formulated. To the extent that this is true, it suggests that the problem of harmful bias cannot be properly addressed without a serious reconsideration of AI driven by LLMs, going back to the foundational assumptions underlying their design.
Accurate text summarization is one of the most common and important tasks performed by Large Language Models, where the costs of human review for an entire document may be high, but the costs of errors in summarization may be even greater. We propose Detecting Errors through Ensembling Prompts (DEEP) - an end-to-end large language model framework for detecting factual errors in text summarization. Our framework uses a diverse set of LLM prompts to identify factual inconsistencies, treating their outputs as binary features, which are then fed into ensembling models. We then calibrate the ensembled models to produce empirically accurate probabilities that a text is factually consistent or free of hallucination. We demonstrate that prior models for detecting factual errors in summaries perform significantly worse without optimizing the thresholds on subsets of the evaluated dataset. Our framework achieves state-of-the-art (SOTA) balanced accuracy on the AggreFact-XSUM FTSOTA, TofuEval Summary-Level, and HaluEval Summarization benchmarks in detecting factual errors within transformer-generated text summaries. It does so without any fine-tuning of the language model or reliance on thresholding techniques not available in practical settings.
Molecular property prediction (MPP) is a fundamental and crucial task in drug discovery. However, prior methods are limited by the requirement for a large number of labeled molecules and their restricted ability to generalize for unseen and new tasks, both of which are essential for real-world applications. To address these challenges, we present MolecularGPT for few-shot MPP. From a perspective on instruction tuning, we fine-tune large language models (LLMs) based on curated molecular instructions spanning over 1000 property prediction tasks. This enables building a versatile and specialized LLM that can be adapted to novel MPP tasks without any fine-tuning through zero- and few-shot in-context learning (ICL). MolecularGPT exhibits competitive in-context reasoning capabilities across 10 downstream evaluation datasets, setting new benchmarks for few-shot molecular prediction tasks. More importantly, with just two-shot examples, MolecularGPT can outperform standard supervised graph neural network methods on 4 out of 7 datasets. It also excels state-of-the-art LLM baselines by up to 15.7% increase on classification accuracy and decrease of 17.9 on regression metrics (e.g., RMSE) under zero-shot. This study demonstrates the potential of LLMs as effective few-shot molecular property predictors. The code is available at https://github.com/NYUSHCS/MolecularGPT.
Dialogue-based Intelligent Tutoring Systems (ITSs) have significantly advanced adaptive and personalized learning by automating sophisticated human tutoring strategies within interactive dialogues. However, replicating the nuanced patterns of expert human communication remains a challenge in Natural Language Processing (NLP). Recent advancements in NLP, particularly Large Language Models (LLMs) such as OpenAI's GPT-4, offer promising solutions by providing human-like and context-aware responses based on extensive pre-trained knowledge. Motivated by the effectiveness of LLMs in various educational tasks (e.g., content creation and summarization, problem-solving, and automated feedback provision), our study introduces the Socratic Playground for Learning (SPL), a dialogue-based ITS powered by the GPT-4 model, which employs the Socratic teaching method to foster critical thinking among learners. Through extensive prompt engineering, SPL can generate specific learning scenarios and facilitates efficient multi-turn tutoring dialogues. The SPL system aims to enhance personalized and adaptive learning experiences tailored to individual needs, specifically focusing on improving critical thinking skills. Our pilot experimental results from essay writing tasks demonstrate SPL has the potential to improve tutoring interactions and further enhance dialogue-based ITS functionalities. Our study, exemplified by SPL, demonstrates how LLMs enhance dialogue-based ITSs and expand the accessibility and efficacy of educational technologies.
Due to accelerating urbanization, the importance of solving the signal control problem increases. This paper analyzes various existing methods and suggests options for increasing the number of agents to reduce the average travel time. Experiments were carried out with 2 datasets. The results show that in some cases, the implementation of multiple agents can improve existing methods. For a fine-tuned large language model approach there is small enhancement on all metrics.
Graphical User Interface (or simply UI) is a primary mean of interaction between users and their devices. In this paper, we discuss three complementary Artificial Intelligence (AI) approaches for triggering the creativity of app designers and inspiring them create better and more diverse UI designs. First, designers can prompt a Large Language Model (LLM) to directly generate and adjust UIs. Second, a Vision-Language Model (VLM) enables designers to effectively search a large screenshot dataset, e.g. from apps published in app stores. Third, a Diffusion Model (DM) can be trained to specifically generate UIs as inspirational images. We present an AI-inspired design process and discuss the implications and limitations of the approaches.
Travel choice analysis is crucial for understanding individual travel behavior to develop appropriate transport policies and recommendation systems in Intelligent Transportation Systems (ITS). Despite extensive research, this domain faces two critical challenges: a) modeling with limited survey data, and b) simultaneously achieving high model explainability and accuracy. In this paper, we introduce a novel prompt-learning-based Large Language Model(LLM) framework that significantly improves prediction accuracy and provides explicit explanations for individual predictions. This framework involves three main steps: transforming input variables into textual form; building of demonstrations similar to the object, and applying these to a well-trained LLM. We tested the framework's efficacy using two widely used choice datasets: London Passenger Mode Choice (LPMC) and Optima-Mode collected in Switzerland. The results indicate that the LLM significantly outperforms state-of-the-art deep learning methods and discrete choice models in predicting people's choices. Additionally, we present a case of explanation illustrating how the LLM framework generates understandable and explicit explanations at the individual level.
In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size, posing significant challenges for widespread deployment. Knowledge distillation (KD) provides a solution by transferring knowledge from a large teacher model to a smaller student model. In this paper, we explore the task-specific distillation of LLMs at the logit level. Our investigation reveals that the logits of fine-tuned LLMs exhibit a more extreme long-tail distribution than those from vision models, with hidden "noise" in the long tail affecting distillation performance. Furthermore, existing logits distillation methods often struggle to effectively utilize the internal ranking information from the logits. To address these, we propose the Bi-directional Logits Difference (BiLD) loss. The BiLD loss filters out the long-tail noise by utilizing only top-$k$ teacher and student logits, and leverages the internal logits ranking information by constructing logits differences. To evaluate BiLD loss, we conduct comprehensive experiments on 13 datasets using two types of LLMs. Our results show that the BiLD loss, with only the top-8 logits, outperforms supervised fine-tuning (SFT), vanilla KL loss, and five other distillation methods from both NLP and CV fields.
The Large Language Model (LLM) has gained significant popularity and is extensively utilized across various domains. Most LLM deployments occur within cloud data centers, where they encounter substantial response delays and incur high costs, thereby impacting the Quality of Services (QoS) at the network edge. Leveraging vector database caching to store LLM request results at the edge can substantially mitigate response delays and cost associated with similar requests, which has been overlooked by previous research. Addressing these gaps, this paper introduces a novel Vector database-assisted cloud-Edge collaborative LLM QoS Optimization (VELO) framework. Firstly, we propose the VELO framework, which ingeniously employs vector database to cache the results of some LLM requests at the edge to reduce the response time of subsequent similar requests. Diverging from direct optimization of the LLM, our VELO framework does not necessitate altering the internal structure of LLM and is broadly applicable to diverse LLMs. Subsequently, building upon the VELO framework, we formulate the QoS optimization problem as a Markov Decision Process (MDP) and devise an algorithm grounded in Multi-Agent Reinforcement Learning (MARL) to decide whether to request the LLM in the cloud or directly return the results from the vector database at the edge. Moreover, to enhance request feature extraction and expedite training, we refine the policy network of MARL and integrate expert demonstrations. Finally, we implement the proposed algorithm within a real edge system. Experimental findings confirm that our VELO framework substantially enhances user satisfaction by concurrently diminishing delay and resource consumption for edge users utilizing LLMs.
In spoken Task-Oriented Dialogue (TOD) systems, the choice of the semantic representation describing the users' requests is key to a smooth interaction. Indeed, the system uses this representation to reason over a database and its domain knowledge to choose its next action. The dialogue course thus depends on the information provided by this semantic representation. While textual datasets provide fine-grained semantic representations, spoken dialogue datasets fall behind. This paper provides insights into automatic enhancement of spoken dialogue datasets' semantic representations. Our contributions are three fold: (1) assess the relevance of Large Language Model fine-tuning, (2) evaluate the knowledge captured by the produced annotations and (3) highlight semi-automatic annotation implications.
Large Language Models (LLMs) have significantly enhanced Information Retrieval (IR) across various modules, such as reranking. Despite impressive performance, current zero-shot relevance ranking with LLMs heavily relies on human prompt engineering. Existing automatic prompt engineering algorithms primarily focus on language modeling and classification tasks, leaving the domain of IR, particularly reranking, underexplored. Directly applying current prompt engineering algorithms to relevance ranking is challenging due to the integration of query and long passage pairs in the input, where the ranking complexity surpasses classification tasks. To reduce human effort and unlock the potential of prompt optimization in reranking, we introduce a novel automatic prompt engineering algorithm named APEER. APEER iteratively generates refined prompts through feedback and preference optimization. Extensive experiments with four LLMs and ten datasets demonstrate the substantial performance improvement of APEER over existing state-of-the-art (SoTA) manual prompts. Furthermore, we find that the prompts generated by APEER exhibit better transferability across diverse tasks and LLMs.
Question Answering (QA) datasets have been instrumental in developing and evaluating Large Language Model (LLM) capabilities. However, such datasets are scarce for languages other than English due to the cost and difficulties of collection and manual annotation. This means that producing novel models and measuring the performance of multilingual LLMs in low-resource languages is challenging. To mitigate this, we propose $\textbf{S}$yn$\textbf{DAR}$in, a method for generating and validating QA datasets for low-resource languages. We utilize parallel content mining to obtain $\textit{human-curated}$ paragraphs between English and the target language. We use the English data as context to $\textit{generate}$ synthetic multiple-choice (MC) question-answer pairs, which are automatically translated and further validated for quality. Combining these with their designated non-English $\textit{human-curated}$ paragraphs form the final QA dataset. The method allows to maintain the content quality, reduces the likelihood of factual errors, and circumvents the need for costly annotation. To test the method, we created a QA dataset with $1.2$K samples for the Armenian language. The human evaluation shows that $98\%$ of the generated English data maintains quality and diversity in the question types and topics, while the translation validation pipeline can filter out $\sim70\%$ of data with poor quality. We use the dataset to benchmark state-of-the-art LLMs, showing their inability to achieve human accuracy with some model performances closer to random chance. This shows that the generated dataset is non-trivial and can be used to evaluate reasoning capabilities in low-resource language.
Navigating historical narratives poses a challenge in unveiling the spatial intricacies of past landscapes. The proposed work addresses this challenge within the context of the English Lake District, employing the Corpus of the Lake District Writing. The method utilizes a generative pre-trained transformer model to extract spatial relations from the textual descriptions in the corpus. The study applies this large language model to understand the spatial dimensions inherent in historical narratives comprehensively. The outcomes are presented as semantic triples, capturing the nuanced connections between entities and locations, and visualized as a network, offering a graphical representation of the spatial narrative. The study contributes to a deeper comprehension of the English Lake District's spatial tapestry and provides an approach to uncovering spatial relations within diverse historical contexts.
In this paper, we introduce LiveMind, a novel low-latency inference framework for large language model (LLM) inference which enables LLMs to perform inferences with incomplete user input. By reallocating computational processes to the input phase, a substantial reduction in latency is achieved, thereby significantly enhancing the interactive experience for users of LLMs. The framework adeptly manages the visibility of the streaming input to the model, allowing it to infer from incomplete user input or await additional content. Compared with traditional inference methods on complete user input, our approach demonstrates an average reduction in response latency of 84.0% on the MMLU dataset and 71.6% on the MMLU-Pro dataset, while maintaining comparable accuracy. Additionally, our framework facilitates collaborative inference and output across different models. By employing an large LLM for inference and a small LLM for output, we achieve an average 37% reduction in response latency, alongside a 4.30% improvement in accuracy on the MMLU-Pro dataset compared with the baseline. The proposed LiveMind framework advances the field of human-AI interaction by enabling more responsive and efficient communication between users and AI systems.
We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demonstrate the equivalence of compression length under arithmetic coding with cumulative negative log probabilities when using a large language model as a prior, that is, the pre-training phase of the model is essentially the process of learning the optimal coding length. At the same time, the evaluation metric compression ratio can be obtained without actual compression, which greatly saves overhead. In this paper, we use five large language models as priors for compression, then compare their performance on challenging natural language processing tasks, including sentence completion, question answering, and coreference resolution. Experimental results show that compression ratio and model performance are positively correlated, so it can be used as a general metric to evaluate large language models.
Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for empowering large language model (LLM) applications. Compared with the supervised training process of LLMs, the RLHF training process is much more sophisticated, requiring a diverse range of computation workloads with intricate dependencies between multiple LLM instances. Therefore, simply adopting the fixed parallelization strategies from supervised training for LLMs can be insufficient for RLHF and result in low training efficiency. To overcome this limitation, we propose a novel technique named parameter ReaLlocation, which dynamically adapts the parallelization strategies for different workloads during training by redistributing LLM parameters across the training cluster. Building upon this idea, we introduce ReaL, a pioneering system for efficient RLHF training. ReaL introduces the concept of an execution plan, which defines a fine-grained resource allocation and parallelization strategy particularly designed for RLHF training. Based on this concept, ReaL employs a tailored search algorithm with a lightweight run-time estimator to automatically discover an efficient execution plan for an instance of RLHF experiment. Subsequently, the runtime engine deploys the selected plan by effectively parallelizing computations and redistributing parameters. We evaluate ReaL on the LLaMA models with up to 70 billion parameters and 128 GPUs. The experimental results demonstrate that ReaL achieves speedups of up to $3.58\times$ compared to baseline methods. Furthermore, the execution plans generated by ReaL exhibit an average of $81\%$ performance improvement over heuristic approaches based on Megatron-LM in the long-context scenario. The source code of ReaL is publicly available at https://github.com/openpsi-project/ReaLHF .
What makes a good Large Language Model (LLM)? That it performs well on the relevant benchmarks -- which hopefully measure, with some validity, the presence of capabilities that are also challenged in real application. But what makes the model perform well? What gives a model its abilities? We take a recently introduced type of benchmark that is meant to challenge capabilities in a goal-directed, agentive context through self-play of conversational games, and analyse how performance develops as a function of model characteristics like number of parameters, or type of training. We find that while there is a clear relationship between number of parameters and performance, there is still a wide spread of performance points within a given size bracket, which is to be accounted for by training parameters such as fine-tuning data quality and method. From a more practical angle, we also find a certain degree of unpredictability about performance across access methods, possible due to unexposed sampling parameters, and a, very welcome, performance stability against at least moderate weight quantisation during inference.
Due to the rapid advancement of Large Language Model (LLM), the whole community eagerly consumes any available text data in order to train the LLM. Currently, large portion of the available text data are collected from internet, which has been thought as a cheap source of the training data. However, when people try to extend the LLM's capability to the personal related domain, such as healthcare or education, the lack of public dataset in these domains make the adaption of the LLM in such domains much slower. The reason of lacking public available dataset in such domains is because they usually contain personal sensitive information. In order to comply with privacy law, the data in such domains need to be de-identified before any kind of dissemination. It had been much research tried to address this problem for the image or tabular data. However, there was limited research on the efficient and general de-identification method for text data. Most of the method based on human annotation or predefined category list. It usually can not be easily adapted to specific domains. The goal of this proposal is to develop a text de-identification framework, which can be easily adapted to the specific domain, leverage the existing expert knowledge without further human annotation. We propose an aspect-based utility-preserved de-identification summarization framework, AspirinSum, by learning to align expert's aspect from existing comment data, it can efficiently summarize the personal sensitive document by extracting personal sensitive aspect related sub-sentence and de-identify it by substituting it with similar aspect sub-sentence. We envision that the de-identified text can then be used in data publishing, eventually publishing our de-identified dataset for downstream task use.
Recently, large language models (LLMs) with extensive general knowledge and powerful reasoning abilities have seen rapid development and widespread application. A systematic and reliable evaluation of LLMs or vision-language model (VLMs) is a crucial step in applying and developing them for various fields. There have been some early explorations about the usability of LLMs for limited urban tasks, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data, the complexity of application scenarios and the highly dynamic nature of the urban environment. In this paper, we design CityBench, an interactive simulator based evaluation platform, as the first systematic benchmark for evaluating the capabilities of LLMs for diverse tasks in urban research. First, we build CityData to integrate the diverse urban data and CitySimu to simulate fine-grained urban dynamics. Based on CityData and CitySimu, we design 8 representative urban tasks in 2 categories of perception-understanding and decision-making as the CityBench. With extensive results from 30 well-known LLMs and VLMs in 13 cities around the world, we find that advanced LLMs and VLMs can achieve competitive performance in diverse urban tasks requiring commonsense and semantic understanding abilities, e.g., understanding the human dynamics and semantic inference of urban images. Meanwhile, they fail to solve the challenging urban tasks requiring professional knowledge and high-level reasoning abilities, e.g., geospatial prediction and traffic control task. These observations provide valuable perspectives for utilizing and developing LLMs in the future. Codes are openly accessible via https://github.com/tsinghua-fib-lab/CityBench.
Accurate load forecasting is crucial for maintaining the power balance between generators and consumers,particularly with the increasing integration of renewable energy sources, which introduce significant intermittent volatility. With the advancement of data-driven methods, machine learning and deep learning models have become the predominant approaches for load forecasting tasks. In recent years, pre-trained large language models (LLMs) have achieved significant progress, demonstrating superior performance across various fields. This paper proposes a load forecasting method based on LLMs, offering not only precise predictive capabilities but also broad and flexible applicability. Additionally, a data modeling method is introduced to effectively transform load sequence data into natural language suitable for LLM training. Furthermore, a data enhancement strategy is designed to mitigate the impact of LLM hallucinations on forecasting results. The effectiveness of the proposed method is validated using two real-world datasets. Compared to existing methods, our approach demonstrates state-of-the-art performance across all validation metrics.