Large language models (LLMs) have emerged as powerful tools for many AI problems and exhibit remarkable in-context learning (ICL) capabilities. Compositional ability, solving unseen complex tasks that combine two or more simple tasks, is an essential reasoning ability for Artificial General Intelligence. Despite the tremendous success of LLMs, how they approach composite tasks, especially those not encountered during the pretraining phase, remains an open and largely underexplored question. In this study, we delve into the ICL capabilities of LLMs on composite tasks, with only simple tasks as in-context examples. We develop a test suite of composite tasks including linguistic and logical challenges and perform empirical studies across different LLM families. We observe that models exhibit divergent behaviors: (1) For simpler composite tasks that apply distinct mapping mechanisms to different input segments, the models demonstrate decent compositional ability, while scaling up the model enhances this ability; (2) for more complex composite tasks involving reasoning multiple steps, where each step represents one task, models typically underperform, and scaling up generally provides no improvements. We offer theoretical analysis in a simplified setting, explaining that models exhibit compositional capability when the task handles different input parts separately. We believe our work sheds new light on the capabilities of LLMs in solving composite tasks regarding the nature of the tasks and model scale. Our dataset and code are available at {\url{https://github.com/OliverXUZY/LLM_Compose}}.
Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in benchmarking code efficiency is a hurdle across varying hardware specifications for popular interpreted languages such as Python. In this paper, we present ECCO, a reproducible benchmark for evaluating program efficiency via two paradigms: natural language (NL) based code generation and history-based code editing. On ECCO, we adapt and thoroughly investigate the three most promising existing LLM-based approaches: in-context learning, iterative refinement with execution or NL feedback, and fine-tuning conditioned on execution and editing history. While most methods degrade functional correctness and moderately increase program efficiency, we find that adding execution information often helps maintain functional correctness, and NL feedback enhances more on efficiency. We release our benchmark to support future work on LLM-based generation of efficient code.
Commercial large language models (LLMs), like OpenAI's GPT-4 powering ChatGPT and Anthropic's Claude 3 Opus, have dominated natural language processing (NLP) benchmarks across different domains. New competing Open-Source alternatives like Mixtral 8x7B or Llama 3 have emerged and seem to be closing the gap while often offering higher throughput and being less costly to use. Open-Source LLMs can also be self-hosted, which makes them interesting for enterprise and clinical use cases where sensitive data should not be processed by third parties. We participated in the 12th BioASQ challenge, which is a retrieval augmented generation (RAG) setting, and explored the performance of current GPT models Claude 3 Opus, GPT-3.5-turbo and Mixtral 8x7b with in-context learning (zero-shot, few-shot) and QLoRa fine-tuning. We also explored how additional relevant knowledge from Wikipedia added to the context-window of the LLM might improve their performance. Mixtral 8x7b was competitive in the 10-shot setting, both with and without fine-tuning, but failed to produce usable results in the zero-shot setting. QLoRa fine-tuning and Wikipedia context did not lead to measurable performance gains. Our results indicate that the performance gap between commercial and open-source models in RAG setups exists mainly in the zero-shot setting and can be closed by simply collecting few-shot examples for domain-specific use cases. The code needed to rerun these experiments is available through GitHub.
Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context Learning (ICL) to explore the potential of large language models (LLMs) for their extensive knowledge and complex reasoning abilities. However, these efforts are inadequate in understanding mulitmodal data and exploiting LLMs' knowledge for product bundling. To bridge the gap, we introduce Bundle-MLLM, a novel framework that fine-tunes LLMs through a hybrid item tokenization approach within a well-designed optimization strategy. Specifically, we integrate textual, media, and relational data into a unified tokenization, introducing a soft separation token to distinguish between textual and non-textual tokens. Additionally, a streamlined yet powerful multimodal fusion module is employed to embed all non-textual features into a single, informative token, significantly boosting efficiency. To tailor product bundling tasks for LLMs, we reformulate the task as a multiple-choice question with candidate items as options. We further propose a progressive optimization strategy that fine-tunes LLMs for disentangled objectives: 1) learning bundle patterns and 2) enhancing multimodal semantic understanding specific to product bundling. Extensive experiments on four datasets across two domains demonstrate that our approach outperforms a range of state-of-the-art (SOTA) methods.
Large Language Models (LLMs) have led to significant improvements in the Knowledge Base Question Answering (KBQA) task. However, datasets used in KBQA studies do not capture the true complexity of KBQA tasks. They either have simple questions, use synthetically generated logical forms, or are based on small knowledge base (KB) schemas. We introduce the SPINACH dataset, an expert-annotated KBQA dataset collected from discussions on Wikidata's "Request a Query" forum with 320 decontextualized question-SPARQL pairs. The complexity of these in-the-wild queries calls for a KBQA system that can dynamically explore large and often incomplete schemas and reason about them, as it is infeasible to create a comprehensive training dataset. We also introduce an in-context learning KBQA agent, also called SPINACH, that mimics how a human expert would write SPARQLs to handle challenging questions. SPINACH achieves a new state of the art on the QALD-7, QALD-9 Plus and QALD-10 datasets by 31.0%, 27.0%, and 10.0% in $F_1$, respectively, and coming within 1.6% of the fine-tuned LLaMA SOTA model on WikiWebQuestions. On our new SPINACH dataset, the SPINACH agent outperforms all baselines, including the best GPT-4-based KBQA agent, by at least 38.1% in $F_1$.
Despite the advances in the abstractive summarization task using Large Language Models (LLM), there is a lack of research that asses their abilities to easily adapt to different domains. We evaluate the domain adaptation abilities of a wide range of LLMs on the summarization task across various domains in both fine-tuning and in-context learning settings. We also present AdaptEval, the first domain adaptation evaluation suite. AdaptEval includes a domain benchmark and a set of metrics to facilitate the analysis of domain adaptation. Our results demonstrate that LLMs exhibit comparable performance in the in-context learning setting, regardless of their parameter scale.
As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level. Recently, inspired by In-Context Learning (ICL), several generalist segmentation frameworks have been proposed, providing a promising paradigm for segmenting specific objects. However, existing works mostly ignore the value of visual prompts or simply apply similarity sorting to select contextual examples. In this paper, we focus on rethinking and improving the example selection strategy. By comprehensive comparisons, we first demonstrate that ICL-based segmentation models are sensitive to different contexts. Furthermore, empirical evidence indicates that the diversity of contextual prompts plays a crucial role in guiding segmentation. Based on the above insights, we propose a new stepwise context search method. Different from previous works, we construct a small yet rich candidate pool and adaptively search the well-matched contexts. More importantly, this method effectively reduces the annotation cost by compacting the search space. Extensive experiments show that our method is an effective strategy for selecting examples and enhancing segmentation performance.
Existing agents based on large language models (LLMs) demonstrate robust problem-solving capabilities by integrating LLMs' inherent knowledge, strong in-context learning and zero-shot capabilities, and the use of tools combined with intricately designed LLM invocation workflows by humans. However, these agents still exhibit shortcomings in long-term reasoning and under-use the potential of existing tools, leading to noticeable deficiencies in complex real-world reasoning scenarios. To address these limitations, we introduce Sibyl, a simple yet powerful LLM-based agent framework designed to tackle complex reasoning tasks by efficiently leveraging a minimal set of tools. Drawing inspiration from Global Workspace Theory, Sibyl incorporates a global workspace to enhance the management and sharing of knowledge and conversation history throughout the system. Furthermore, guided by Society of Mind Theory, Sibyl implements a multi-agent debate-based jury to self-refine the final answers, ensuring a comprehensive and balanced approach. This approach aims to reduce system complexity while expanding the scope of problems solvable-from matters typically resolved by humans in minutes to those requiring hours or even days, thus facilitating a shift from System-1 to System-2 thinking. Sibyl has been designed with a focus on scalability and ease of debugging by incorporating the concept of reentrancy from functional programming from its inception, with the aim of seamless and low effort integration in other LLM applications to improve capabilities. Our experimental results on the GAIA benchmark test set reveal that the Sibyl agent instantiated with GPT-4 achieves state-of-the-art performance with an average score of 34.55%, compared to other agents based on GPT-4. We hope that Sibyl can inspire more reliable and reusable LLM-based agent solutions to address complex real-world reasoning tasks.
Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Originating from the simple 'retrieve-then-read' approach, the RAG framework has evolved into a highly flexible and modular paradigm. A critical component, the Query Rewriter module, enhances knowledge retrieval by generating a search-friendly query. This method aligns input questions more closely with the knowledge base. Our research identifies opportunities to enhance the Query Rewriter module to Query Rewriter+ by generating multiple queries to overcome the Information Plateaus associated with a single query and by rewriting questions to eliminate Ambiguity, thereby clarifying the underlying intent. We also find that current RAG systems exhibit issues with Irrelevant Knowledge; to overcome this, we propose the Knowledge Filter. These two modules are both based on the instruction-tuned Gemma-2B model, which together enhance response quality. The final identified issue is Redundant Retrieval; we introduce the Memory Knowledge Reservoir and the Retriever Trigger to solve this. The former supports the dynamic expansion of the RAG system's knowledge base in a parameter-free manner, while the latter optimizes the cost for accessing external knowledge, thereby improving resource utilization and response efficiency. These four RAG modules synergistically improve the response quality and efficiency of the RAG system. The effectiveness of these modules has been validated through experiments and ablation studies across six common QA datasets. The source code can be accessed at https://github.com/Ancientshi/ERM4.
Few-Shot Relation Extraction (FSRE), a subtask of Relation Extraction (RE) that utilizes limited training instances, appeals to more researchers in Natural Language Processing (NLP) due to its capability to extract textual information in extremely low-resource scenarios. The primary methodologies employed for FSRE have been fine-tuning or prompt tuning techniques based on Pre-trained Language Models (PLMs). Recently, the emergence of Large Language Models (LLMs) has prompted numerous researchers to explore FSRE through In-Context Learning (ICL). However, there are substantial limitations associated with methods based on either traditional RE models or LLMs. Traditional RE models are hampered by a lack of necessary prior knowledge, while LLMs fall short in their task-specific capabilities for RE. To address these shortcomings, we propose a Dual-System Augmented Relation Extractor (DSARE), which synergistically combines traditional RE models with LLMs. Specifically, DSARE innovatively injects the prior knowledge of LLMs into traditional RE models, and conversely enhances LLMs' task-specific aptitude for RE through relation extraction augmentation. Moreover, an Integrated Prediction module is employed to jointly consider these two respective predictions and derive the final results. Extensive experiments demonstrate the efficacy of our proposed method.
Large language models (LLMs) have garnered unprecedented advancements across diverse fields, ranging from natural language processing to computer vision and beyond. The prowess of LLMs is underpinned by their substantial model size, extensive and diverse datasets, and the vast computational power harnessed during training, all of which contribute to the emergent abilities of LLMs (e.g., in-context learning) that are not present in small models. Within this context, the mixture of experts (MoE) has emerged as an effective method for substantially scaling up model capacity with minimal computation overhead, gaining significant attention from academia and industry. Despite its growing prevalence, there lacks a systematic and comprehensive review of the literature on MoE. This survey seeks to bridge that gap, serving as an essential resource for researchers delving into the intricacies of MoE. We first briefly introduce the structure of the MoE layer, followed by proposing a new taxonomy of MoE. Next, we overview the core designs for various MoE models including both algorithmic and systemic aspects, alongside collections of available open-source implementations, hyperparameter configurations and empirical evaluations. Furthermore, we delineate the multifaceted applications of MoE in practice, and outline some potential directions for future research. To facilitate ongoing updates and the sharing of cutting-edge developments in MoE research, we have established a resource repository accessible at https://github.com/withinmiaov/A-Survey-on-Mixture-of-Experts.
Despite much work on advanced deep learning and generative modeling techniques for tabular data generation and imputation, traditional methods have continued to win on imputation benchmarks. We herein present UnmaskingTrees, a simple method for tabular imputation (and generation) employing gradient-boosted decision trees which are used to incrementally unmask individual features. This approach offers state-of-the-art performance on imputation, and on generation given training data with missingness; and it has competitive performance on vanilla generation. To solve the conditional generation subproblem, we propose a tabular probabilistic prediction method, BaltoBot, which fits a balanced tree of boosted tree classifiers. Unlike older methods, it requires no parametric assumption on the conditional distribution, accommodating features with multimodal distributions; unlike newer diffusion methods, it offers fast sampling, closed-form density estimation, and flexible handling of discrete variables. We finally consider our two approaches as meta-algorithms, demonstrating in-context learning-based generative modeling with TabPFN.
Recurrent large language models that compete with Transformers in language modeling perplexity are emerging at a rapid rate (e.g., Mamba, RWKV). Excitingly, these architectures use a constant amount of memory during inference. However, due to the limited memory, recurrent LMs cannot recall and use all the information in long contexts leading to brittle in-context learning (ICL) quality. A key challenge for efficient LMs is selecting what information to store versus discard. In this work, we observe the order in which information is shown to the LM impacts the selection difficulty. To formalize this, we show that the hardness of information recall reduces to the hardness of a problem called set disjointness (SD), a quintessential problem in communication complexity that requires a streaming algorithm (e.g., recurrent model) to decide whether inputted sets are disjoint. We empirically and theoretically show that the recurrent memory required to solve SD changes with set order, i.e., whether the smaller set appears first in-context. Our analysis suggests, to mitigate the reliance on data order, we can put information in the right order in-context or process prompts non-causally. Towards that end, we propose: (1) JRT-Prompt, where context gets repeated multiple times in the prompt, effectively showing the model all data orders. This gives $11.0 \pm 1.3$ points of improvement, averaged across $16$ recurrent LMs and the $6$ ICL tasks, with $11.9\times$ higher throughput than FlashAttention-2 for generation prefill (length $32$k, batch size $16$, NVidia H100). We then propose (2) JRT-RNN, which uses non-causal prefix-linear-attention to process prompts and provides $99\%$ of Transformer quality at $360$M params., $30$B tokens and $96\%$ at $1.3$B params., $50$B tokens on average across the tasks, with $19.2\times$ higher throughput for prefill than FA2.
The consequences of a healthcare data breach can be devastating for the patients, providers, and payers. The average financial impact of a data breach in recent months has been estimated to be close to USD 10 million. This is especially significant for healthcare organizations in India that are managing rapid digitization while still establishing data governance procedures that align with the letter and spirit of the law. Computer-based systems for de-identification of personal information are vulnerable to data drift, often rendering them ineffective in cross-institution settings. Therefore, a rigorous assessment of existing de-identification against local health datasets is imperative to support the safe adoption of digital health initiatives in India. Using a small set of de-identified patient discharge summaries provided by an Indian healthcare institution, in this paper, we report the nominal performance of de-identification algorithms (based on language models) trained on publicly available non-Indian datasets, pointing towards a lack of cross-institutional generalization. Similarly, experimentation with off-the-shelf de-identification systems reveals potential risks associated with the approach. To overcome data scarcity, we explore generating synthetic clinical reports (using publicly available and Indian summaries) by performing in-context learning over Large Language Models (LLMs). Our experiments demonstrate the use of generated reports as an effective strategy for creating high-performing de-identification systems with good generalization capabilities.
In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a large pool of labeled examples often entails significant annotation costs. To address this challenge, we propose Sub-SA (Submodular Selective Annotation), a submodule-based selective annotation method. The aim of Sub-SA is to reduce annotation costs while improving the quality of in-context examples and minimizing the time consumption of the selection process. In Sub-SA, we design a submodular function that facilitates effective subset selection for annotation and demonstrates the characteristics of monotonically and submodularity from the theoretical perspective. Specifically, we propose RPR (Reward and Penalty Regularization) to better balance the diversity and representativeness of the unlabeled dataset attributed to a reward term and a penalty term, respectively. Consequently, the selection for annotations can be effectively addressed with a simple yet effective greedy search algorithm based on the submodular function. Finally, we apply the similarity prompt retrieval to get the examples for ICL.
**FunAudioLLM**은 인간과 대규모 언어 모델(LLM) 간의 자연스러운 음성 상호작용을 향상시키기 위해 개발된 혁신적인 모델 패밀리이다. 이 모델은 두 가지 주요 구성 요소인 **SenseVoice**와 **CosyVoice**로 이루어져 있다. **SenseVoice**는 다국어 음성 인식, 감정 인식, 오디오 이벤트 감지 기능을 제공하며, **SenseVoice-Small**과 **SenseVoice-Large** 두 가지 변형이 있다. **SenseVoice-Small**은 5개 언어에 대해 낮은 지연 시간의 자동 음성 인식(ASR)을 지원하며, **SenseVoice-Large**는 50개 이상의 언어에 대한 고정밀 ASR을 가능하게 한다. 이러한 성능은 Whisper 모델들에 비해 상당한 속도 향상을 보여준다.
**CosyVoice**는 자연스러운 음성을 생성하는 데 중점을 두고 있으며, 다국어 음성 생성, 제로샷 문맥 내 학습, 크로스링구얼 음성 클로닝 및 지시 따르기 기능을 갖추고 있다. 이 모델은 특정 화자에 맞춘 음성 생성을 가능하게 하여 사용자 맞춤형 음성 출력을 지원한다. 두 모델 모두 오픈소스로 공개되어 있어, 연구자와 개발자들이 쉽게 접근하고 활용할 수 있도록 하였다.
**FunAudioLLM**은 이러한 모델들을 LLM과 통합하여 음성-음성 번역, 감정 음성 채팅, 인터랙티브 팟캐스트 및 표현력이 풍부한 오디오북 내레이션과 같은 다양한 응용 프로그램을 가능하게 한다. 이러한 혁신은 음성 상호작용 기술의 경계를 확장하며, 사용자에게 보다 직관적이고 인간적인 경험을 제공한다. 그러나 모델의 한계로는 자원이 부족한 언어에 대한 ASR 성능 저하와 감정 및 말하기 스타일의 명시적 지침 없이 추론하는 데 어려움이 있다. 이러한 문제는 향후 연구의 중요한 방향이 될 것이다.
결론적으로, **FunAudioLLM**은 음성 이해 및 생성의 새로운 패러다임을 제시하며, 인간과 기계 간의 상호작용을 보다 자연스럽고 효율적으로 만들어 줄 것으로 기대된다.
Pretrained transformers exhibit the remarkable ability of in-context learning (ICL): they can learn tasks from just a few examples provided in the prompt without updating any weights. This raises a foundational question: can ICL solve fundamentally $\textit{new}$ tasks that are very different from those seen during pretraining? To probe this question, we examine ICL's performance on linear regression while varying the diversity of tasks in the pretraining dataset. We empirically demonstrate a $\textit{task diversity threshold}$ for the emergence of ICL. Below this threshold, the pretrained transformer cannot solve unseen regression tasks, instead behaving like a Bayesian estimator with the $\textit{non-diverse pretraining task distribution}$ as the prior. Beyond this threshold, the transformer significantly outperforms this estimator; its behavior aligns with that of ridge regression, corresponding to a Gaussian prior over $\textit{all tasks}$, including those not seen during pretraining. Thus, when pretrained on data with task diversity greater than the threshold, transformers $\textit{can}$ optimally solve fundamentally new tasks in-context. Importantly, this capability hinges on it deviating from the Bayes optimal estimator with the pretraining distribution as the prior. This study also explores the effect of regularization, model capacity and task structure and underscores, in a concrete example, the critical role of task diversity, alongside data and model scale, in the emergence of ICL. Code is available at https://github.com/mansheej/icl-task-diversity.
Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) using images that portray point distributions on a two-dimensional plane. We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these combinatorial challenges. Our experimental investigation includes rigorous evaluations across zero-shot settings and introduces innovative multi-agent zero-shot in-context scenarios. The results demonstrated that both multi-agent models. Multi-Agent 1, which includes the Initializer, Critic, and Scorer agents, and Multi-Agent 2, which comprises only the Initializer and Critic agents; significantly improved solution quality for TSP and mTSP problems. Multi-Agent 1 excelled in environments requiring detailed route refinement and evaluation, providing a robust framework for sophisticated optimizations. In contrast, Multi-Agent 2, focusing on iterative refinements by the Initializer and Critic, proved effective for rapid decision-making scenarios. These experiments yield promising outcomes, showcasing the robust visual reasoning capabilities of MLLMs in addressing diverse combinatorial problems. The findings underscore the potential of MLLMs as powerful tools in computational optimization, offering insights that could inspire further advancements in this promising field. Project link: https://github.com/ahmed-abdulhuy/Solving-TSP-and-mTSP-Combinatorial-Challenges-using-Visual-Reasoning-and-Multi-Agent-Approach-MLLMs-.git
The process mining community has recently recognized the potential of large language models (LLMs) for tackling various process mining tasks. Initial studies report the capability of LLMs to support process analysis and even, to some extent, that they are able to reason about how processes work. This latter property suggests that LLMs could also be used to tackle process mining tasks that benefit from an understanding of process behavior. Examples of such tasks include (semantic) anomaly detection and next activity prediction, which both involve considerations of the meaning of activities and their inter-relations. In this paper, we investigate the capabilities of LLMs to tackle such semantics-aware process mining tasks. Furthermore, whereas most works on the intersection of LLMs and process mining only focus on testing these models out of the box, we provide a more principled investigation of the utility of LLMs for process mining, including their ability to obtain process mining knowledge post-hoc by means of in-context learning and supervised fine-tuning. Concretely, we define three process mining tasks that benefit from an understanding of process semantics and provide extensive benchmarking datasets for each of them. Our evaluation experiments reveal that (1) LLMs fail to solve challenging process mining tasks out of the box and when provided only a handful of in-context examples, (2) but they yield strong performance when fine-tuned for these tasks, consistently surpassing smaller, encoder-based language models.
Small Language Models (SLMs) are generally considered more compact versions of large language models (LLMs). This study investigates the ability of SLMs with parameters between 1 and 3 billion to learn, retain, and subsequently eliminate different types of noise present in the data. Four pre-trained SLMs were utilized for this: Olmo 1B, Qwen1.5 1.8B, Gemma 2B, and Phi2 2.7B. The models were instruction-tuned on noise-free data and tested using in-context examples to determine if they could learn noise through examples. Subsequently, noise patterns were introduced in instruction tuning to evaluate the noise learning, unlearning, and retention capabilities of the models. Olmo, the smallest model, was highly sensitive to noise, quickly adapting to noisy patterns. Phi2 resisted learning character-level and transliteration noise, likely due to its carefully curated, structured, and high-quality pretraining data. Gemma excelled with transliteration noise, likely benefiting from its multilingual pretraining. The findings can be used to develop robust training strategies for SLMs.