CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

Large language models (LLMs) are often augmented with tools to solve complex tasks. By generating code snippets and executing them through task-specific Application Programming Interfaces (APIs), they can offload certain functions to dedicated external modules, such as image encoding and performing calculations. However, most existing approaches to augment LLMs with tools are constrained by general-purpose APIs and lack the flexibility for tailoring them to specific tasks. In this work, we present CRAFT, a general tool creation and retrieval framework for LLMs. It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. For each task, we collect specific code solutions by prompting GPT-4 to solve the training examples. Following a validation step ensuring the correctness, these solutions are abstracted into code snippets to enhance reusability, and deduplicated for higher quality. At inference time, the language model retrieves snippets from the toolsets and then executes them or generates the output conditioning on the retrieved snippets. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning. Experiments on vision-language, tabular processing, and mathematical reasoning tasks show that our approach achieves substantial improvements compared to strong baselines. In addition, our in-depth analysis reveals that: (1) consistent performance improvement can be achieved by scaling up the number of tools and the capability of the backbone models; (2) each component of our approach contributes to the performance gains; (3) the created tools are well-structured and reliable with low complexity and atomicity. The code is available at \url{https://github.com/lifan-yuan/CRAFT}.

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

To solve complex tasks, large language models (LLMs) often require multiple rounds of interactions with the user, sometimes assisted by external tools. However, current evaluation paradigms often focus solely on benchmark performance with single-turn exchanges, neglecting the intricate interactions among the user, LLMs, and external tools, creating a discrepancy between benchmark evaluation and real-world use cases. We introduce MINT benchmark to evaluate LLMs' ability to solve tasks with multi-turn interactions by (1) using tools and (2) leveraging natural language feedback. To ensure reproducibility, we provide an evaluation framework where LLMs can access tools by executing Python code and receive natural language feedback from the user simulated with GPT-4. We repurpose a diverse set of established datasets and tasks focusing on reasoning, coding, and decision-making and carefully curate them into a compact subset of instances for efficient evaluation. Our analysis of 20 open- and closed-source LLMs offers intriguing findings. (1) LLMs generally benefit from tool interactions and language feedback, with performance gains (absolute, same below) of 1--8% per additional turn with tool use and 2--17% with natural language feedback. (2) Better single-turn performance does not guarantee better multi-turn performance. (3) Surprisingly, on LLMs we evaluated, we found supervised instruction-finetuning (SIFT) and reinforcement learning from human feedback (RLHF) generally hurt multi-turn capabilities. We hope MINT can help measure progress and incentivize research in improving LLMs' capabilities in multi-turn interactions, especially for open-source communities where multi-turn human evaluation has been less accessible compared to commercial LLMs with a larger user base.

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models

Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to demonstrate human-like reasoning based on the perceived information. To address a crucial concern regarding the extent to which their reasoning capabilities are fully consistent and grounded, we also measure the reasoning consistency of these models. We achieve this by proposing a chain-of-thought (CoT) based consistency measure. However, such an evaluation requires a benchmark that encompasses both high-level inference and detailed reasoning chains, which is costly. We tackle this challenge by proposing a LLM-Human-in-the-Loop pipeline, which notably reduces cost while simultaneously ensuring the generation of a high-quality dataset. Based on this pipeline and the existing coarse-grained annotated dataset, we build the CURE benchmark to measure both the zero-shot reasoning performance and consistency of VLMs. We evaluate existing state-of-the-art VLMs, and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency, indicating that substantial efforts are required to enable VLMs to perform visual reasoning as systematically and consistently as humans. As an early step, we propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs. The first stage involves employing supervised fine-tuning of VLMs using step-by-step reasoning samples automatically generated by LLMs. In the second stage, we further augment the training process by incorporating feedback provided by LLMs to produce reasoning chains that are highly consistent and grounded. We empirically highlight the effectiveness of our framework in both reasoning performance and consistency.

LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models

In recent years, there have been remarkable advancements in the performance of Transformer-based Large Language Models (LLMs) across various domains. As these LLMs are deployed for increasingly complex tasks, they often face the need to conduct longer reasoning processes or understand larger contexts. In these situations, the length generalization failure of LLMs on long sequences becomes more prominent. Most pre-training schemes truncate training sequences to a fixed length. LLMs often struggle to generate fluent and coherent texts, let alone carry out downstream tasks, after longer contexts, even with relative positional encoding designed to cope with this problem. Common solutions such as finetuning on longer corpora often involve daunting hardware and time costs and require careful training process design. To more efficiently leverage the generation capacity of existing LLMs, we theoretically and empirically investigate the main out-of-distribution (OOD) factors contributing to this problem. Inspired by this diagnosis, we propose a simple yet effective solution for on-the-fly length generalization, LM-Infinite. It involves only a $\Lambda$-shaped attention mask (to avoid excessive attended tokens) and a distance limit (to avoid unseen distances) while requiring no parameter updates or learning. We find it applicable to a variety of LLMs using relative-position encoding methods. LM-Infinite is computationally efficient with $O(n)$ time and space, and demonstrates consistent text generation fluency and quality to as long as 32k tokens on ArXiv and OpenWebText2 datasets, with 2.72x decoding speedup. On downstream tasks such as passkey retrieval, it continues to work on inputs much longer than training lengths where vanilla models fail immediately.

Making Pre-trained Language Models both Task-solvers and Self-calibrators

Pre-trained language models (PLMs) serve as backbones for various real-world systems. For high-stake applications, it's equally essential to have reasonable confidence estimations in predictions. While the vanilla confidence scores of PLMs can already be effectively utilized, PLMs consistently become overconfident in their wrong predictions, which is not desirable in practice. Previous work shows that introducing an extra calibration task can mitigate this issue. The basic idea involves acquiring additional data to train models in predicting the confidence of their initial predictions. However, it only demonstrates the feasibility of this kind of method, assuming that there are abundant extra available samples for the introduced calibration task. In this work, we consider the practical scenario that we need to effectively utilize training samples to make PLMs both task-solvers and self-calibrators. Three challenges are presented, including limited training samples, data imbalance, and distribution shifts. We first conduct pilot experiments to quantify various decisive factors in the calibration task. Based on the empirical analysis results, we propose a training algorithm LM-TOAST to tackle the challenges. Experimental results show that LM-TOAST can effectively utilize the training data to make PLMs have reasonable confidence estimations while maintaining the original task performance. Further, we consider three downstream applications, namely selective classification, adversarial defense, and model cascading, to show the practical usefulness of LM-TOAST. The code will be made public at \url{https://github.com/Yangyi-Chen/LM-TOAST}.

Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This paper aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.

Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among different cognitive processes yield superior outcomes compared to individual cognitive processes in isolation. Although Large Language Models (LLMs) have demonstrated promising performance as general task-solving agents, they still struggle with tasks that require intensive domain knowledge and complex reasoning. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist refers to an intelligent agent that collaborates with multiple minds, combining their individual strengths and knowledge, to enhance problem-solving and overall performance in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. We have discovered that assigning multiple, fine-grained personas in LLMs elicits better problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, SPP effectively elicits internal knowledge acquisition abilities, reduces hallucination, and maintains strong reasoning capabilities. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.

Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification

Event schemas are a form of world knowledge about the typical progression of events. Recent methods for event schema induction use information extraction systems to construct a large number of event graph instances from documents, and then learn to generalize the schema from such instances. In contrast, we propose to treat event schemas as a form of commonsense knowledge that can be derived from large language models (LLMs). This new paradigm greatly simplifies the schema induction process and allows us to handle both hierarchical relations and temporal relations between events in a straightforward way. Since event schemas have complex graph structures, we design an incremental prompting and verification method to break down the construction of a complex event graph into three stages: event skeleton construction, event expansion, and event-event relation verification. Compared to directly using LLMs to generate a linearized graph, our method can generate large and complex schemas with 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations. In addition, compared to the previous state-of-the-art closed-domain schema induction model, human assessors were able to cover $\sim$10% more events when translating the schemas into coherent stories and rated our schemas 1.3 points higher (on a 5-point scale) in terms of readability.