Prominent large language models have exhibited human-level performance in many domains, even enabling the derived agents to simulate human and social interactions. While practical works have substantiated the practicability of grounding language agents in sandbox simulation or embodied simulators, current social intelligence benchmarks either stay at the language level or use subjective metrics. In pursuit of a more realistic and objective evaluation, we introduce the Social Tasks in Sandbox Simulation (STSS) benchmark, which assesses language agents \textbf{objectively} at the \textbf{action level} by scrutinizing the goal achievements within the multi-agent simulation. Additionally, we sample conversation scenarios to build a language-level benchmark to provide an economically prudent preliminary evaluation and align with prevailing benchmarks. To gauge the significance of agent architecture, we implement a target-driven planning (TDP) module as an adjunct to the existing agent. Our evaluative findings highlight that the STSS benchmark is challenging for state-of-the-art language agents. Furthermore, it effectively discriminates between distinct language agents, suggesting its usefulness as a benchmark for evaluating both language models and agent architectures.

To enhance the performance of large language models (LLM) on downstream tasks, one solution is to fine-tune certain LLM parameters and make it better align with the characteristics of the training dataset. This process is commonly known as parameter-efficient fine-tuning (PEFT). Due to the scale of LLM, PEFT operations are usually executed in the public environment (e.g., cloud server). This necessitates the sharing of sensitive user data across public environments, thereby raising potential privacy concerns. To tackle these challenges, we propose a distributed PEFT framework called DLoRA. DLoRA enables scalable PEFT operations to be performed collaboratively between the cloud and user devices. Coupled with the proposed Kill and Revive algorithm, the evaluation results demonstrate that DLoRA can significantly reduce the computation and communication workload over the user devices while achieving superior accuracy and privacy protection.

Finetuning pretrained models on downstream generation tasks often leads to catastrophic forgetting in zero-shot conditions. In this work, we focus on summarization and tackle the problem through the lens of language-independent representations. After training on monolingual summarization, we perform zero-shot transfer to new languages or language pairs. We first show naively finetuned models are highly language-specific in both output behavior and internal representations, resulting in poor zero-shot performance. Next, we propose query-key (QK) finetuning to decouple task-specific knowledge from the pretrained language generation abilities. Then, after showing downsides of the standard adversarial language classifier, we propose a balanced variant that more directly enforces language-agnostic representations. Moreover, our qualitative analyses show removing source language identity correlates to zero-shot summarization performance. Our code is openly available.

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally require 2-4$\times$ times more parameters to achieve comparable performance to a dense model, which incurs larger GPU memory requirements and makes MoE models less efficient in I/O-bounded scenarios like autoregressive generation. In this work, we propose a hybrid dense training and sparse inference framework for MoE models (DS-MoE) which achieves strong computation and parameter efficiency by employing dense computation across all experts during training and sparse computation during inference. Our experiments on training LLMs demonstrate that our DS-MoE models are more parameter-efficient than standard sparse MoEs and are on par with dense models in terms of total parameter size and performance while being computationally cheaper (activating 30-40% of the model's parameters). Performance tests using vLLM show that our DS-MoE-6B model runs up to $1.86\times$ faster than similar dense models like Mistral-7B, and between $1.50\times$ and $1.71\times$ faster than comparable MoEs, such as DeepSeekMoE-16B and Qwen1.5-MoE-A2.7B.

In e-commerce, opinion summarization is the process of summarizing the consensus opinions found in product reviews. However, the potential of additional sources such as product description and question-answers (QA) has been considered less often. Moreover, the absence of any supervised training data makes this task challenging. To address this, we propose a novel synthetic dataset creation (SDC) strategy that leverages information from reviews as well as additional sources for selecting one of the reviews as a pseudo-summary to enable supervised training. Our Multi-Encoder Decoder framework for Opinion Summarization (MEDOS) employs a separate encoder for each source, enabling effective selection of information while generating the summary. For evaluation, due to the unavailability of test sets with additional sources, we extend the Amazon, Oposum+, and Flipkart test sets and leverage ChatGPT to annotate summaries. Experiments across nine test sets demonstrate that the combination of our SDC approach and MEDOS model achieves on average a 14.5% improvement in ROUGE-1 F1 over the SOTA. Moreover, comparative analysis underlines the significance of incorporating additional sources for generating more informative summaries. Human evaluations further indicate that MEDOS scores relatively higher in coherence and fluency with 0.41 and 0.5 (-1 to 1) respectively, compared to existing models. To the best of our knowledge, we are the first to generate opinion summaries leveraging additional sources in a self-supervised setting.

Large Language Models (LLMs) are undergoing a period of rapid updates and changes, with state-of-the-art (SOTA) model frequently being replaced. When applying LLMs to a specific scientific field, it's challenging to acquire unique domain knowledge while keeping the model itself advanced. To address this challenge, a sophisticated large language model system named as Xiwu has been developed, allowing you switch between the most advanced foundation models and quickly teach the model domain knowledge. In this work, we will report on the best practices for applying LLMs in the field of high-energy physics (HEP), including: a seed fission technology is proposed and some data collection and cleaning tools are developed to quickly obtain domain AI-Ready dataset; a just-in-time learning system is implemented based on the vector store technology; an on-the-fly fine-tuning system has been developed to facilitate rapid training under a specified foundation model. The results show that Xiwu can smoothly switch between foundation models such as LLaMA, Vicuna, ChatGLM and Grok-1. The trained Xiwu model is significantly outperformed the benchmark model on the HEP knowledge question-and-answering and code generation. This strategy significantly enhances the potential for growth of our model's performance, with the hope of surpassing GPT-4 as it evolves with the development of open-source models. This work provides a customized LLM for the field of HEP, while also offering references for applying LLM to other fields, the corresponding codes are available on Github.

Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed for general multimodal tasks, failing to capture the unique characteristics of web pages, or focus on end-to-end web agent tasks, unable to measure fine-grained abilities such as OCR, understanding, and grounding. In this paper, we introduce VisualWebBench, a multimodal benchmark designed to assess the capabilities of MLLMs across a variety of web tasks. VisualWebBench consists of seven tasks, and comprises 1.5K human-curated instances from 139 real websites, covering 87 sub-domains. We evaluate 14 open-source MLLMs, Gemini Pro, Claude-3 series, and GPT-4V(ision) on VisualWebBench, revealing significant challenges and performance gaps. Further analysis highlights the limitations of current MLLMs, including inadequate grounding in text-rich environments and subpar performance with low-resolution image inputs. We believe VisualWebBench will serve as a valuable resource for the research community and contribute to the creation of more powerful and versatile MLLMs for web-related applications.

Background: The integration of artificial intelligence (AI) into daily life, particularly through chatbots utilizing natural language processing (NLP), presents both revolutionary potential and unique challenges. This intended to investigate how different input forms impact ChatGPT, a leading language model by OpenAI, performance in understanding and executing complex, multi-intention tasks. Design: Employing a case study methodology supplemented by discourse analysis, the research analyzes ChatGPT's responses to inputs varying from natural language to pseudo-code engineering. The study specifically examines the model's proficiency across four categories: understanding of intentions, interpretability, completeness, and creativity. Setting and Participants: As a theoretical exploration of AI interaction, this study focuses on the analysis of structured and unstructured inputs processed by ChatGPT, without direct human participants. Data collection and analysis: The research utilizes synthetic case scenarios, including the organization of a "weekly meal plan" and a "shopping list," to assess ChatGPT's response to prompts in both natural language and pseudo-code engineering. The analysis is grounded in the identification of patterns, contradictions, and unique response elements across different input formats. Results: Findings reveal that pseudo-code engineering inputs significantly enhance the clarity and determinism of ChatGPT's responses, reducing ambiguity inherent in natural language. Enhanced natural language, structured through prompt engineering techniques, similarly improves the model's interpretability and creativity. Conclusions: The study underscores the potential of pseudo-code engineering in refining human-AI interaction and achieving more deterministic, concise, and direct outcomes, advocating for its broader application across disciplines requiring precise AI responses.

Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation. However, it is unclear how meaningful the notion of "zero-shot" generalization is for such multimodal models, as it is not known to what extent their pretraining datasets encompass the downstream concepts targeted for during "zero-shot" evaluation. In this work, we ask: How is the performance of multimodal models on downstream concepts influenced by the frequency of these concepts in their pretraining datasets? We comprehensively investigate this question across 34 models and five standard pretraining datasets (CC-3M, CC-12M, YFCC-15M, LAION-400M, LAION-Aesthetics), generating over 300GB of data artifacts. We consistently find that, far from exhibiting "zero-shot" generalization, multimodal models require exponentially more data to achieve linear improvements in downstream "zero-shot" performance, following a sample inefficient log-linear scaling trend. This trend persists even when controlling for sample-level similarity between pretraining and downstream datasets, and testing on purely synthetic data distributions. Furthermore, upon benchmarking models on long-tailed data sampled based on our analysis, we demonstrate that multimodal models across the board perform poorly. We contribute this long-tail test set as the "Let it Wag!" benchmark to further research in this direction. Taken together, our study reveals an exponential need for training data which implies that the key to "zero-shot" generalization capabilities under large-scale training paradigms remains to be found.

We present a large language model (LLM) based system to empower quadrupedal robots with problem-solving abilities for long-horizon tasks beyond short-term motions. Long-horizon tasks for quadrupeds are challenging since they require both a high-level understanding of the semantics of the problem for task planning and a broad range of locomotion and manipulation skills to interact with the environment. Our system builds a high-level reasoning layer with large language models, which generates hybrid discrete-continuous plans as robot code from task descriptions. It comprises multiple LLM agents: a semantic planner for sketching a plan, a parameter calculator for predicting arguments in the plan, and a code generator to convert the plan into executable robot code. At the low level, we adopt reinforcement learning to train a set of motion planning and control skills to unleash the flexibility of quadrupeds for rich environment interactions. Our system is tested on long-horizon tasks that are infeasible to complete with one single skill. Simulation and real-world experiments show that it successfully figures out multi-step strategies and demonstrates non-trivial behaviors, including building tools or notifying a human for help.