Large language models exhibit societal biases associated with demographic information, including race, gender, and others. Endowing such language models with personalities based on demographic data can enable generating opinions that align with those of humans. Building on this idea, we propose "random silicon sampling," a method to emulate the opinions of the human population sub-group. Our study analyzed 1) a language model that generates the survey responses that correspond with a human group based solely on its demographic distribution and 2) the applicability of our methodology across various demographic subgroups and thematic questions. Through random silicon sampling and using only group-level demographic information, we discovered that language models can generate response distributions that are remarkably similar to the actual U.S. public opinion polls. Moreover, we found that the replicability of language models varies depending on the demographic group and topic of the question, and this can be attributed to inherent societal biases in the models. Our findings demonstrate the feasibility of mirroring a group's opinion using only demographic distribution and elucidate the effect of social biases in language models on such simulations.

This study assesses four cutting-edge language models in the underexplored Aminoacian language. Through evaluation, it scrutinizes their adaptability, effectiveness, and limitations in text generation, semantic coherence, and contextual understanding. Uncovering insights into these models' performance in a low-resourced language, this research pioneers pathways to bridge linguistic gaps. By offering benchmarks and understanding challenges, it lays groundwork for future advancements in natural language processing, aiming to elevate the applicability of language models in similar linguistic landscapes, marking a significant step toward inclusivity and progress in language technology.

Large language models (LLMs) have demonstrated impressive performance on many tasks. However, to achieve optimal performance, specially designed prompting methods are still needed. These methods either rely on task-specific few-shot examples that require a certain level of domain knowledge, or are designed to be simple but only perform well on a few types of tasks. In this work, we attempt to introduce the concept of generalist prompting, which operates on the design principle of achieving optimal or near-optimal performance on a wide range of tasks while eliminating the need for manual selection and customization of prompts tailored to specific problems. Furthermore, we propose MeMo (Mental Models), an innovative prompting method that is simple-designed yet effectively fulfills the criteria of generalist prompting. MeMo distills the cores of various prompting methods into individual mental models and allows LLMs to autonomously select the most suitable mental models for the problem, achieving or being near to the state-of-the-art results on diverse tasks such as STEM, logical reasoning, and commonsense reasoning in zero-shot settings. We hope that the insights presented herein will stimulate further exploration of generalist prompting methods for LLMs.

Drawing inspiration from the remarkable This paper introduces diffusion protein language progress in NLP achieved by language models (LMs; Devlin model (DPLM), a versatile protein language et al., 2019; Radford et al., 2018; OpenAI, 2023) thanks to model that demonstrates strong generative and the scalability of Transformers (Vaswani et al., 2017) and predictive capabilities for protein sequences. We the existence of large-scale text data, recent explorations in first pre-train scalable DPLMs from evolutionaryscale protein has also demonstrated the impressive capabilities of protein sequences within a generative selfsupervised protein language models (Rives et al., 2019; Lin et al., 2022; discrete diffusion probabilistic framework, Hu et al., 2022), learned from the universe of evolutionaryscale which generalizes language modeling for protein sequences. As a result, protein LMs have proteins in a principled way. After pre-training, become one of the most important cornerstones in AI for DPLM exhibits the ability to generate structurally protein research, serving a pivotal role not only in predictive plausible, novel and diverse protein sequences tasks (e.g., probing functional properties, and predicting for unconditional generation. We further protein structures from single sequences without explicit demonstrate the proposed diffusion generative evolutionary homologs) but also in generative tasks (e.g., pre-training make DPLM possess a better redesigning sequences given protein backbone structures, or understanding of proteins, making it a superior synthesizing completely new protein sequences).

In this work, we introduce a new unsupervised embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model fine-tuning or taskspecific engineering. Leveraging meta-task prompting, MetaEOL guides LLMs to produce embeddings through a series of carefully designed prompts that address multiple representational aspects. Our comprehensive experiments demonstrate that embeddings averaged from various meta-tasks yield competitive performance Figure 1: The highest decoding probabilities are largely on Semantic Textual Similarity (STS) allocated to stop words that carry little useful information benchmarks and excel in downstream tasks, when conducting a meaning compression prompting, surpassing contrastive-trained models. Our even if employing a constraint of "in one word" findings suggest a new scaling law for embedding following (Jiang et al., 2023b). Although the general generation, offering a versatile, resourceefficient semantic, movie, is contained, other aspects of this sentence approach for embedding extraction are missing, like sentiments.

Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms. These include gradient descent, classification, sequence completion, transformation, and improvement. In this work, we investigate whether large language models (LLMs), which never explicitly encountered the task of black-box optimization, are in principle capable of implementing evolutionary optimization algorithms. While previous works have solely focused on language-based task specification, we move forward and focus on the zero-shot application of LLMs to black-box optimization. We introduce a novel prompting strategy, consisting of least-to-most sorting of discretized population members and querying the LLM to propose an improvement to the mean statistic, i.e. perform a type of black-box recombination operation. Empirically, we find that our setup allows the user to obtain an LLM-based evolution strategy, which we call `EvoLLM', that robustly outperforms baseline algorithms such as random search and Gaussian Hill Climbing on synthetic BBOB functions as well as small neuroevolution tasks. Hence, LLMs can act as `plug-in' in-context recombination operators. We provide several comparative studies of the LLM's model size, prompt strategy, and context construction. Finally, we show that one can flexibly improve EvoLLM's performance by providing teacher algorithm information via instruction fine-tuning on previously collected teacher optimization trajectories.

Parameter-efficient finetuning (PEFT) is a widely used technique to adapt large language models for different tasks. Service providers typically create separate systems for users to perform PEFT model finetuning and inference tasks. This is because existing systems cannot handle workloads that include a mix of inference and PEFT finetuning requests. As a result, shared GPU resources are underutilized, leading to inefficiencies. To address this problem, we present FlexLLM, the first system that can serve inference and parameter-efficient finetuning requests in the same iteration. Our system leverages the complementary nature of these two tasks and utilizes shared GPU resources to run them jointly, using a method called co-serving. To achieve this, FlexLLM introduces a novel token-level finetuning mechanism, which breaks down the finetuning computation of a sequence into smaller token-level computations and uses dependent parallelization and graph pruning, two static compilation optimizations, to minimize the memory overhead and latency for co-serving. Compared to existing systems, FlexLLM's co-serving approach reduces the activation GPU memory overhead by up to 8x, and the end-to-end GPU memory requirement of finetuning by up to 36% while maintaining a low inference latency and improving finetuning throughput. For example, under a heavy inference workload, FlexLLM can still preserve more than 80% of the peak finetuning throughput, whereas existing systems cannot make any progress with finetuning. The source code of FlexLLM is publicly available at https://github.com/flexflow/FlexFlow.

Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts. When interacting in real-world scenarios, the decision-making abilities of a role significantly shape its behavioral patterns. In this paper, we concentrate on evaluating the decision-making abilities of LLMs post role-playing thereby validating the efficacy of role-playing. Our goal is to provide metrics and guidance for enhancing the decision-making abilities of LLMs in role-playing tasks. Specifically, we first use LLMs to generate virtual role descriptions corresponding to the 16 personality types of Myers-Briggs Type Indicator (abbreviated as MBTI) representing a segmentation of the population. Then we design specific quantitative operations to evaluate the decision-making abilities of LLMs post role-playing from four aspects: adaptability, exploration$\&$exploitation trade-off ability, reasoning ability, and safety. Finally, we analyze the association between the performance of decision-making and the corresponding MBTI types through GPT-4. Extensive experiments demonstrate stable differences in the four aspects of decision-making abilities across distinct roles, signifying a robust correlation between decision-making abilities and the roles emulated by LLMs. These results underscore that LLMs can effectively impersonate varied roles while embodying their genuine sociological characteristics.

With contributions from the open-source community, a vast amount of instruction tuning (IT) data has emerged. Given the significant resource allocation required by training and evaluating models, it is advantageous to have an efficient method for selecting high-quality IT data. However, existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. In this paper, we propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR). CaR consists of two steps. The first step involves ranking instruction pairs using a scoring model that is well aligned with expert preferences (achieving an accuracy of 84.25%). The second step involves preserving dataset diversity through a clustering process.In our experiment, CaR selected a subset containing only 1.96% of Alpaca's IT data, yet the underlying AlpaCaR model trained on this subset outperforms Alpaca by an average of 32.1% in GPT-4 evaluations. Furthermore, our method utilizes small models (355M parameters) and requires only 11.2% of the monetary cost compared to existing methods, making it easily deployable in industrial scenarios.

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat models, there do not exist defenses that provide robustness against semantic attacks and avoid unfavorable trade-offs between robustness and nominal performance. To meet this need, we propose SEMANTICSMOOTH, a smoothing-based defense that aggregates the predictions of multiple semantically transformed copies of a given input prompt. Experimental results demonstrate that SEMANTICSMOOTH achieves state-of-the-art robustness against GCG, PAIR, and AutoDAN attacks while maintaining strong nominal performance on instruction following benchmarks such as InstructionFollowing and AlpacaEval. The codes will be publicly available at https://github.com/UCSB-NLP-Chang/SemanticSmooth.