With Large Language Models (LLMs) being widely used across various tasks, detecting errors in their responses is increasingly crucial. However, little research has been conducted on error detection of LLM responses. Collecting error annotations on LLM responses is challenging due to the subjective nature of many NLP tasks, and thus previous research focuses on tasks of little practical value (e.g., word sorting) or limited error types (e.g., faithfulness in summarization). This work introduces ReaLMistake, the first error detection benchmark consisting of objective, realistic, and diverse errors made by LLMs. ReaLMistake contains three challenging and meaningful tasks that introduce objectively assessable errors in four categories (reasoning correctness, instruction-following, context-faithfulness, and parameterized knowledge), eliciting naturally observed and diverse errors in responses of GPT-4 and Llama 2 70B annotated by experts. We use ReaLMistake to evaluate error detectors based on 12 LLMs. Our findings show: 1) Top LLMs like GPT-4 and Claude 3 detect errors made by LLMs at very low recall, and all LLM-based error detectors perform much worse than humans. 2) Explanations by LLM-based error detectors lack reliability. 3) LLMs-based error detection is sensitive to small changes in prompts but remains challenging to improve. 4) Popular approaches to improving LLMs, including self-consistency and majority vote, do not improve the error detection performance. Our benchmark and code are provided at //github.com/psunlpgroup/ReaLMistake.
相關內容
大語言模型是基于海量文本數據訓練的深度學習模型。它不僅能夠生成自然語言文本，還能夠深入理解文本含義，處理各種自然語言任務，如文本摘要、問答、翻譯等。2023年，大語言模型及其在人工智能領域的應用已成為全球科技研究的熱點，其在規模上的增長尤為引人注目，參數量已從最初的十幾億躍升到如今的一萬億。參數量的提升使得模型能夠更加精細地捕捉人類語言微妙之處，更加深入地理解人類語言的復雜性。在過去的一年里，大語言模型在吸納新知識、分解復雜任務以及圖文對齊等多方面都有顯著提升。隨著技術的不斷成熟，它將不斷拓展其應用范圍，為人類提供更加智能化和個性化的服務，進一步改善人們的生活和生產方式。
Causal models are crucial for understanding complex systems and identifying causal relationships among variables. Even though causal models are extremely popular, conditional probability calculation of formulas involving interventions pose significant challenges. In case of Causal Bayesian Networks (CBNs), Pearl assumes autonomy of mechanisms that determine interventions to calculate a range of probabilities. We show that by making simple yet often realistic independence assumptions, it is possible to uniquely estimate the probability of an interventional formula (including the well-studied notions of probability of sufficiency and necessity). We discuss when these assumptions are appropriate. Importantly, in many cases of interest, when the assumptions are appropriate, these probability estimates can be evaluated using observational data, which carries immense significance in scenarios where conducting experiments is impractical or unfeasible.
In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters using the sign of gradients, resulting in more stable convergence curves. The learning rate and the batch size are the most critical hyperparameters for optimizers, which require careful tuning to enable effective convergence. Previous research has shown that the optimal learning rate increases linearly or follows similar rules with batch size for SGD style optimizers. However, this conclusion is not applicable to Adam style optimizers. In this paper, we elucidate the connection between optimal learning rates and batch sizes for Adam style optimizers through both theoretical analysis and extensive experiments. First, we raise the scaling law between batch sizes and optimal learning rates in the sign of gradient case, in which we prove that the optimal learning rate first rises and then falls as the batch size increases. Moreover, the peak value of the surge will gradually move toward the larger batch size as training progresses. Second, we conducted experiments on various CV and NLP tasks and verified the correctness of the scaling law.
Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements. Weight-only quantization has emerged as a promising solution to address these challenges. Previous research suggests that fine-tuning through up and down rounding can enhance performance. In this study, we introduce SignRound, a method that utilizes signed gradient descent (SignSGD) to optimize rounding values and weight clipping within just 200 steps. SignRound integrates the advantages of Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ), achieving exceptional results across 2 to 4 bits while maintaining low tuning costs and avoiding additional inference overhead. For example, SignRound achieves absolute average accuracy improvements ranging from 6.91\% to 33.22\% at 2 bits. It also demonstrates robust generalization to recent models and achieves near-lossless quantization in most scenarios at 4 bits. The source code is publicly available at \url{//github.com/intel/auto-round}.
Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for natural language interaction within multi-agent systems to foster cooperation. However, LLM agents tend to over-report and comply with any instruction, which may result in information redundancy and confusion in multi-agent cooperation. Inspired by human organizations, this paper introduces a framework that imposes prompt-based organization structures on LLM agents to mitigate these problems. Through a series of experiments with embodied LLM agents and human-agent collaboration, our results highlight the impact of designated leadership on team efficiency, shedding light on the leadership qualities displayed by LLM agents and their spontaneous cooperative behaviors. Further, we harness the potential of LLMs to propose enhanced organizational prompts, via a Criticize-Reflect process, resulting in novel organization structures that reduce communication costs and enhance team efficiency.
The rapid development of collaborative robotics has provided a new possibility of helping the elderly who has difficulties in daily life, allowing robots to operate according to specific intentions. However, efficient human-robot cooperation requires natural, accurate and reliable intention recognition in shared environments. The current paramount challenge for this is reducing the uncertainty of multimodal fused intention to be recognized and reasoning adaptively a more reliable result despite current interactive condition. In this work we propose a novel learning-based multimodal fusion framework Batch Multimodal Confidence Learning for Opinion Pool (BMCLOP). Our approach combines Bayesian multimodal fusion method and batch confidence learning algorithm to improve accuracy, uncertainty reduction and success rate given the interactive condition. In particular, the generic and practical multimodal intention recognition framework can be easily extended further. Our desired assistive scenarios consider three modalities gestures, speech and gaze, all of which produce categorical distributions over all the finite intentions. The proposed method is validated with a six-DoF robot through extensive experiments and exhibits high performance compared to baselines.
As Generative AI rises in adoption, its use has expanded to include domains such as hiring and recruiting. However, without examining the potential of bias, this may negatively impact marginalized populations, including people with disabilities. To address this important concern, we present a resume audit study, in which we ask ChatGPT (specifically, GPT-4) to rank a resume against the same resume enhanced with an additional leadership award, scholarship, panel presentation, and membership that are disability related. We find that GPT-4 exhibits prejudice towards these enhanced CVs. Further, we show that this prejudice can be quantifiably reduced by training a custom GPTs on principles of DEI and disability justice. Our study also includes a unique qualitative analysis of the types of direct and indirect ableism GPT-4 uses to justify its biased decisions and suggest directions for additional bias mitigation work. Additionally, since these justifications are presumably drawn from training data containing real-world biased statements made by humans, our analysis suggests additional avenues for understanding and addressing human bias.
The problem of improving the handover performance in Long Term Evolution-Advanced (LTE-A) networks has not been fully solved yet. Traditionally, the selection of the target Evolved Node B (TeNB) in the handover procedure is based on the signal strength measurements, which may not produce a reliable handover. A reliable handover method may reduce the instances of unstable or frequent handovers that otherwise waste network resources. The signal strength measurement process is inherently time consuming as the user equipment (UE) has to measure multiple neighboring eNB (NeNB) frequencies in each measurement period. An efficient handover method is required to improve the overall performance of such systems. In this paper we propose a reliable and fast TeNB selection scheme for LTE-A handover. The proposed scheme outperforms the existing LTE-A handover methods. The improved performance is achieved by selecting the TeNB based on some three independent parameters, namely orientation matching (OM), current load (CL), and the received signal strengths. An UE essentially measures only the NeNBs shortlisted based on OM and CL; thus measurement time is reduced considerably leading to a reduction of overall handover time. The performance of the proposed scheme is validated by simulation.
Emergence, broadly conceptualized as the ``intelligent'' behaviors of LLMs, has recently been studied and proved challenging to quantify due to the lack of a measurable definition. Most commonly, it has been estimated statistically through model performances across extensive datasets and tasks, which consumes significant resources. In addition, such estimation is difficult to interpret and may not accurately reflect the models' intrinsic emergence. In this work, we propose a quantifiable solution for estimating emergence. Inspired by emergentism in dynamics, we quantify the strength of emergence by comparing the entropy reduction of the macroscopic (semantic) level with that of the microscopic (token) level, both of which are derived from the representations within the transformer block. Using a low-cost estimator, our quantification method demonstrates consistent behaviors across a suite of LMs (GPT-2, GEMMA, etc.) under both in-context learning (ICL) and natural sentences. Empirical results show that (1) our method gives consistent measurements which align with existing observations based on performance metrics, validating the effectiveness of our emergence quantification; (2) our proposed metric uncovers novel emergence patterns such as the correlations between the variance of our metric and the number of ``shots'' in ICL, which further suggests a new way of interpreting hallucinations in LLMs; (3) we offer a potential solution towards estimating the emergence of larger and closed-resource LMs via smaller LMs like GPT-2. Our codes are available at: //github.com/Zodiark-ch/Emergence-of-LLMs/.
This paper considers the problem of Byzantine fault-tolerance in distributed multi-agent optimization. In this problem, each agent has a local cost function, and in the fault-free case, the goal is to design a distributed algorithm that allows all the agents to find a minimum point of all the agents' aggregate cost function. We consider a scenario where some agents might be Byzantine faulty that renders the original goal of computing a minimum point of all the agents' aggregate cost vacuous. A more reasonable objective for an algorithm in this scenario is to allow all the non-faulty agents to compute the minimum point of only the non-faulty agents' aggregate cost. Prior work shows that if there are up to $f$ (out of $n$) Byzantine agents then a minimum point of the non-faulty agents' aggregate cost can be computed exactly if and only if the non-faulty agents' costs satisfy a certain redundancy property called $2f$-redundancy. However, $2f$-redundancy is an ideal property that can be satisfied only in systems free from noise or uncertainties, which can make the goal of exact fault-tolerance unachievable in some applications. Thus, we introduce the notion of $(f,\epsilon)$-resilience, a generalization of exact fault-tolerance wherein the objective is to find an approximate minimum point of the non-faulty aggregate cost, with $\epsilon$ accuracy. This approximate fault-tolerance can be achieved under a weaker condition that is easier to satisfy in practice, compared to $2f$-redundancy. We obtain necessary and sufficient conditions for achieving $(f,\epsilon)$-resilience characterizing the correlation between relaxation in redundancy and approximation in resilience. In case when the agents' cost functions are differentiable, we obtain conditions for $(f,\epsilon)$-resilience of the distributed gradient-descent method when equipped with robust gradient aggregation.
While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from causality toward RL. In particular, we divide existing CRL approaches into two categories according to whether their causality-based information is given in advance or not. We further analyze each category in terms of the formalization of different models, ranging from the Markov Decision Process (MDP), Partially Observed Markov Decision Process (POMDP), Multi-Arm Bandits (MAB), and Dynamic Treatment Regime (DTR). Moreover, we summarize the evaluation matrices and open sources while we discuss emerging applications, along with promising prospects for the future development of CRL.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191