While textual information significantly enhances the performance of pre-trained language models (PLMs) in knowledge graph completion (KGC), the static and noisy nature of existing corpora collected from Wikipedia articles or synsets definitions often limits the potential of PLM-based KGC models. To surmount these challenges, we introduce the Contextualization Distillation strategy, a versatile plug-in-and-play approach compatible with both discriminative and generative KGC frameworks. Our method begins by instructing large language models (LLMs) to transform compact, structural triplets into context-rich segments. Subsequently, we introduce two tailored auxiliary tasks, reconstruction and contextualization, allowing smaller KGC models to assimilate insights from these enriched triplets. Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach, revealing consistent performance enhancements irrespective of underlying pipelines or architectures. Moreover, our analysis makes our method more explainable and provides insight into generating path selection, as well as the choosing of suitable distillation tasks. All the code and data in this work will be released at //github.com/David-Li0406/Contextulization-Distillation
相關內容
Large language models (LLMs) have reached human-like proficiency in generating diverse textual content, underscoring the necessity for effective fake text detection to avoid potential risks such as fake news in social media. Previous research has mostly tested single models on in-distribution datasets, limiting our understanding of how these models perform on different types of data for LLM-generated text detection task. We researched this by testing five specialized transformer-based models on both in-distribution and out-of-distribution datasets to better assess their performance and generalizability. Our results revealed that single transformer-based classifiers achieved decent performance on in-distribution dataset but limited generalization ability on out-of-distribution dataset. To improve it, we combined the individual classifiers models using adaptive ensemble algorithms, which improved the average accuracy significantly from 91.8% to 99.2% on an in-distribution test set and from 62.9% to 72.5% on an out-of-distribution test set. The results indicate the effectiveness, good generalization ability, and great potential of adaptive ensemble algorithms in LLM-generated text detection.
The current evaluation of Large Language Models (LLMs) predominantly relies on benchmarks focusing on their embedded knowledge by testing through multiple-choice questions (MCQs), a format inherently suited for automated evaluation. Our study extends this evaluation to explore LLMs' pragmatic competence--a facet previously underexamined before the advent of sophisticated LLMs, specifically in the context of Korean. We employ two distinct evaluation setups: the conventional MCQ format, adapted for automatic evaluation, and Open-Ended Questions (OEQs), assessed by human experts, to examine LLMs' narrative response capabilities without predefined options. Our findings reveal that GPT-4 excels, scoring 81.11 and 85.69 in the MCQ and OEQ setups, respectively, with HyperCLOVA X, an LLM optimized for Korean, closely following, especially in the OEQ setup, demonstrating a score of 81.56 with a marginal difference of 4.13 points compared to GPT-4. Furthermore, while few-shot learning strategies generally enhance LLM performance, Chain-of-Thought (CoT) prompting introduces a bias toward literal interpretations, hindering accurate pragmatic inference. Considering the growing expectation for LLMs to understand and produce language that aligns with human communicative norms, our findings emphasize the importance for advancing LLMs' abilities to grasp and convey sophisticated meanings beyond mere literal interpretations.
Speech language models (LMs) are promising for high-quality speech synthesis through in-context learning. A typical speech LM takes discrete semantic units as content and a short utterance as prompt, and synthesizes speech which preserves the content's semantics but mimics the prompt's style. However, there is no systematic understanding on how the synthesized audio is controlled by the prompt and content. In this work, we conduct an empirical study of the widely used autoregressive (AR) and non-autoregressive (NAR) speech LMs and provide insights into the prompt design and content semantic units. Our analysis reveals that heterogeneous and nonstationary prompts hurt the audio quality in contrast to the previous finding that longer prompts always lead to better synthesis. Moreover, we find that the speaker style of the synthesized audio is also affected by the content in addition to the prompt. We further show that semantic units carry rich acoustic information such as pitch, tempo, volume and speech emphasis, which might be leaked from the content to the synthesized audio.
Large language models (LLMs) hold immense promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. In this work, we present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions and then conduct an empirical case study with Med-PaLM 2, resulting in the largest human evaluation study in this area to date. Our contributions include a multifactorial framework for human assessment of LLM-generated answers for biases, and EquityMedQA, a collection of seven newly-released datasets comprising both manually-curated and LLM-generated questions enriched for adversarial queries. Both our human assessment framework and dataset design process are grounded in an iterative participatory approach and review of possible biases in Med-PaLM 2 answers to adversarial queries. Through our empirical study, we find that the use of a collection of datasets curated through a variety of methodologies, coupled with a thorough evaluation protocol that leverages multiple assessment rubric designs and diverse rater groups, surfaces biases that may be missed via narrower evaluation approaches. Our experience underscores the importance of using diverse assessment methodologies and involving raters of varying backgrounds and expertise. We emphasize that while our framework can identify specific forms of bias, it is not sufficient to holistically assess whether the deployment of an AI system promotes equitable health outcomes. We hope the broader community leverages and builds on these tools and methods towards realizing a shared goal of LLMs that promote accessible and equitable healthcare for all.
The advent of large vision-language models (LVLMs) represents a noteworthy advancement towards the pursuit of artificial general intelligence. However, the extent of their efficacy across both specialized and general tasks warrants further investigation. This article endeavors to evaluate the competency of popular LVLMs in specialized and general tasks, respectively, aiming to offer a comprehensive comprehension of these innovative methodologies. To gauge their efficacy in specialized tasks, we tailor a comprehensive testbed comprising three distinct scenarios: natural, healthcare, and industrial, encompassing six challenging tasks. These tasks include salient, camouflaged, and transparent object detection, as well as polyp and skin lesion detection, alongside industrial anomaly detection. We examine the performance of three recent open-source LVLMs -- MiniGPT-v2, LLaVA-1.5, and Shikra -- in the realm of visual recognition and localization. Moreover, we conduct empirical investigations utilizing the aforementioned models alongside GPT-4V, assessing their multi-modal understanding capacities in general tasks such as object counting, absurd question answering, affordance reasoning, attribute recognition, and spatial relation reasoning. Our investigations reveal that these models demonstrate limited proficiency not only in specialized tasks but also in general tasks. We delve deeper into this inadequacy and suggest several potential factors, including limited cognition in specialized tasks, object hallucination, text-to-image interference, and decreased robustness in complex problems. We hope this study would provide valuable insights for the future development of LVLMs, augmenting their power in coping with both general and specialized applications.
Alignment with human preference prevents large language models (LLMs) from generating misleading or toxic content while requiring high-cost human feedback. Assuming resources of human annotation are limited, there are two different ways of allocating considered: more diverse PROMPTS or more diverse RESPONSES to be labeled. Nonetheless, a straightforward comparison between their impact is absent. In this work, we first control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their influence. We find that instead of numerous prompts, more responses but fewer prompts better trigger LLMs for human alignment. Additionally, the concept of diversity for prompts can be more complex than responses that are typically quantified by single digits. Consequently, a new formulation of prompt diversity is proposed, further implying a linear correlation with the final performance of LLMs after fine-tuning. We also leverage it on data augmentation and conduct experiments to show its effect on different algorithms.
Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation
Large language models (LLMs) have demonstrated notable proficiency in code generation, with numerous prior studies showing their promising capabilities in various development scenarios. However, these studies mainly provide evaluations in research settings, which leaves a significant gap in understanding how effectively LLMs can support developers in real-world. To address this, we conducted an empirical analysis of conversations in DevGPT, a dataset collected from developers' conversations with ChatGPT (captured with the Share Link feature on platforms such as GitHub). Our empirical findings indicate that the current practice of using LLM-generated code is typically limited to either demonstrating high-level concepts or providing examples in documentation, rather than to be used as production-ready code. These findings indicate that there is much future work needed to improve LLMs in code generation before they can be integral parts of modern software development.
For training an encoder network to perform amortized variational inference, the Kullback-Leibler (KL) divergence from the exact posterior to its approximation, known as the inclusive or forward KL, is an increasingly popular choice of variational objective due to the mass-covering property of its minimizer. However, minimizing this objective is challenging. A popular existing approach, Reweighted Wake-Sleep (RWS), suffers from heavily biased gradients and a circular pathology that results in highly concentrated variational distributions. As an alternative, we propose SMC-Wake, a procedure for fitting an amortized variational approximation that uses likelihood-tempered sequential Monte Carlo samplers to estimate the gradient of the inclusive KL divergence. We propose three gradient estimators, all of which are asymptotically unbiased in the number of iterations and two of which are strongly consistent. Our method interleaves stochastic gradient updates, SMC samplers, and iterative improvement to an estimate of the normalizing constant to reduce bias from self-normalization. In experiments with both simulated and real datasets, SMC-Wake fits variational distributions that approximate the posterior more accurately than existing methods.
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by LLMs are prone to errors, which can subsequently lead to incorrect reasoning during inference. Furthermore, inappropriate exemplars (overly simplistic or complex), can affect overall performance among varying levels of difficulty. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains. By utilizing iterative bootstrapping, our approach enables LLMs to autonomously rectify errors, resulting in more precise and comprehensive reasoning chains. Simultaneously, our approach selects challenging yet answerable questions accompanied by reasoning chains as exemplars with a moderate level of difficulty, which enhances the LLMs' generalizability across varying levels of difficulty. Experimental results indicate that Iter-CoT exhibits superiority, achieving competitive performance across three distinct reasoning tasks on ten datasets.
The commercialization of large language models (LLMs) has led to the common practice of high-level API-only access to proprietary models. In this work, we show that even with a conservative assumption about the model architecture, it is possible to learn a surprisingly large amount of non-public information about an API-protected LLM from a relatively small number of API queries (e.g., costing under $1,000 for OpenAI's gpt-3.5-turbo). Our findings are centered on one key observation: most modern LLMs suffer from a softmax bottleneck, which restricts the model outputs to a linear subspace of the full output space. We show that this lends itself to a model image or a model signature which unlocks several capabilities with affordable cost: efficiently discovering the LLM's hidden size, obtaining full-vocabulary outputs, detecting and disambiguating different model updates, identifying the source LLM given a single full LLM output, and even estimating the output layer parameters. Our empirical investigations show the effectiveness of our methods, which allow us to estimate the embedding size of OpenAI's gpt-3.5-turbo to be about 4,096. Lastly, we discuss ways that LLM providers can guard against these attacks, as well as how these capabilities can be viewed as a feature (rather than a bug) by allowing for greater transparency and accountability.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191