Accurate uncertainty quantification is crucial for the safe deployment of language models (LMs), and prior research has demonstrated improvements in the calibration of modern LMs. Our study focuses on in-context learning (ICL), a prevalent method for adapting static LMs through tailored prompts, and examines the balance between performance and calibration across a broad spectrum of natural language understanding and reasoning tasks. Through comprehensive experiments, we observe that, with an increasing number of ICL examples, models initially exhibit increased miscalibration before achieving better calibration and miscalibration tends to arise in low-shot settings. Moreover, we find that methods aimed at improving usability, such as fine-tuning and chain-of-thought (CoT) prompting, can lead to miscalibration and unreliable natural language explanations, suggesting that new methods may be required for scenarios where models are expected to be reliable.
相關內容
The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous downstream NLP tasks. In this era of open-ended language modeling, where task boundaries are gradually fading, an urgent question emerges: have we made significant advances in text classification under the full benefit of LLMs? To answer this question, we propose RGPT, an adaptive boosting framework tailored to produce a specialized text classification LLM by recurrently ensembling a pool of strong base learners. The base learners are constructed by adaptively adjusting the distribution of training samples and iteratively fine-tuning LLMs with them. Such base learners are then ensembled to be a specialized text classification LLM, by recurrently incorporating the historical predictions from the previous learners. Through a comprehensive empirical comparison, we show that RGPT significantly outperforms 8 SOTA PLMs and 7 SOTA LLMs on four benchmarks by 1.36% on average. Further evaluation experiments show a clear surpassing of RGPT over human classification.
In enhancing the reasoning capabilities of large language models (LLMs), prior research primarily focuses on specific prompting techniques such as few-shot or zero-shot chain-of-thought (CoT) prompting. These methods, while effective, often involve manually intensive prompt engineering. Our study takes a novel approach by asking: Can LLMs reason effectively without prompting? Our findings reveal that, intriguingly, CoT reasoning paths can be elicited from pre-trained LLMs by simply altering the \textit{decoding} process. Rather than conventional greedy decoding, we investigate the top-$k$ alternative tokens, uncovering that CoT paths are frequently inherent in these sequences. This approach not only bypasses the confounders of prompting but also allows us to assess the LLMs' \textit{intrinsic} reasoning abilities. Moreover, we observe that the presence of a CoT in the decoding path correlates with a higher confidence in the model's decoded answer. This confidence metric effectively differentiates between CoT and non-CoT paths. Extensive empirical studies on various reasoning benchmarks show that the proposed CoT-decoding substantially outperforms the standard greedy decoding.
Mutation validation (MV) is a recently proposed approach for model selection, garnering significant interest due to its unique characteristics and potential benefits compared to the widely used cross-validation (CV) method. In this study, we empirically compared MV and $k$-fold CV using benchmark and real-world datasets. By employing Bayesian tests, we compared generalization estimates yielding three posterior probabilities: practical equivalence, CV superiority, and MV superiority. We also evaluated the differences in the capacity of the selected models and computational efficiency. We found that both MV and CV select models with practically equivalent generalization performance across various machine learning algorithms and the majority of benchmark datasets. MV exhibited advantages in terms of selecting simpler models and lower computational costs. However, in some cases MV selected overly simplistic models leading to underfitting and showed instability in hyperparameter selection. These limitations of MV became more evident in the evaluation of a real-world neuroscientific task of predicting sex at birth using brain functional connectivity.
The rapid rise in popularity of Large Language Models (LLMs) with emerging capabilities has spurred public curiosity to evaluate and compare different LLMs, leading many researchers to propose their LLM benchmarks. Noticing preliminary inadequacies in those benchmarks, we embarked on a study to critically assess 23 state-of-the-art LLM benchmarks, using our novel unified evaluation framework through the lenses of people, process, and technology, under the pillars of functionality and security. Our research uncovered significant limitations, including biases, difficulties in measuring genuine reasoning, adaptability, implementation inconsistencies, prompt engineering complexity, evaluator diversity, and the overlooking of cultural and ideological norms in one comprehensive assessment. Our discussions emphasized the urgent need for standardized methodologies, regulatory certainties, and ethical guidelines in light of Artificial Intelligence (AI) advancements, including advocating for an evolution from static benchmarks to dynamic behavioral profiling to accurately capture LLMs' complex behaviors and potential risks. Our study highlighted the necessity for a paradigm shift in LLM evaluation methodologies, underlining the importance of collaborative efforts for the development of universally accepted benchmarks and the enhancement of AI systems' integration into society.
Recently, the potential of large language models (LLMs) has been widely used in assisting programming. However, current research does not explore the artist potential of LLMs in creative coding within artist and AI collaboration. Our work probes the reflection type of artists in the creation process with such collaboration. We compare two common collaboration approaches: invoking the entire program and multiple subtasks. Our findings exhibit artists' different stimulated reflections in two different methods. Our finding also shows the correlation of reflection type with user performance, user satisfaction, and subjective experience in two collaborations through conducting two methods, including experimental data and qualitative interviews. In this sense, our work reveals the artistic potential of LLM in creative coding. Meanwhile, we provide a critical lens of human-AI collaboration from the artists' perspective and expound design suggestions for future work of AI-assisted creative tasks.
We propose some new results on the comparison of the minimum or maximum order statistic from a random number of non-identical random variables. Under the non-identical set-up, with certain conditions, we prove that random minimum (maximum) of one system dominates the other in hazard rate (reversed hazard rate) order. Further, we prove variation diminishing property (Karlin [8]) for all possible restrictions to derive the new results.
To evaluate code large language models (LLMs), research has relied on a few small manually curated benchmarks, such as HumanEval and MBPP, which represent a narrow part of the real-world software domains. In this work, we introduce round-trip correctness (RTC) as an alternative evaluation method. RTC allows Code LLM evaluation on a broader spectrum of real-world software domains without the need for costly human curation. RTC rests on the idea that we can ask a model to make a prediction (e.g., describe some code using natural language), feed that prediction back (e.g., synthesize code from the predicted description), and check if this round-trip leads to code that is semantically equivalent to the original input. We show how to employ RTC to evaluate code synthesis and editing. We find that RTC strongly correlates with model performance on existing narrow-domain code synthesis benchmarks while allowing us to expand to a much broader set of domains and tasks which was not previously possible without costly human annotations.
Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limitations. In order to address these challenges, researchers have pursued two primary strategies, knowledge editing and retrieval augmentation, to enhance LLMs by incorporating external information from different aspects. Nevertheless, there is still a notable absence of a comprehensive survey. In this paper, we propose a review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications. In addition, we conduct an in-depth analysis of different methods and point out potential research directions in the future. We hope this survey offers the community quick access and a comprehensive overview of this research area, with the intention of inspiring future research endeavors.
Recently, graph neural networks have been gaining a lot of attention to simulate dynamical systems due to their inductive nature leading to zero-shot generalizability. Similarly, physics-informed inductive biases in deep-learning frameworks have been shown to give superior performance in learning the dynamics of physical systems. There is a growing volume of literature that attempts to combine these two approaches. Here, we evaluate the performance of thirteen different graph neural networks, namely, Hamiltonian and Lagrangian graph neural networks, graph neural ODE, and their variants with explicit constraints and different architectures. We briefly explain the theoretical formulation highlighting the similarities and differences in the inductive biases and graph architecture of these systems. We evaluate these models on spring, pendulum, gravitational, and 3D deformable solid systems to compare the performance in terms of rollout error, conserved quantities such as energy and momentum, and generalizability to unseen system sizes. Our study demonstrates that GNNs with additional inductive biases, such as explicit constraints and decoupling of kinetic and potential energies, exhibit significantly enhanced performance. Further, all the physics-informed GNNs exhibit zero-shot generalizability to system sizes an order of magnitude larger than the training system, thus providing a promising route to simulate large-scale realistic systems.
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called Scientific Information Extractor (SciIE) for with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191