Praveen Venkateswaran’s research while affiliated with IBM Research - Thomas J. Watson Research Center and other places

Developers using LLMs in their applications and agents have provided plenty of anecdotal evidence that in-context-learning (ICL) is fragile. In addition to the quantity and quality of examples, we show that the order in which the in-context examples are listed in the prompt affects the output of the LLM and, consequently, their performance. In this paper, we present OptiSeq, which introduces a score based on log probabilities of LLM outputs to prune the universe of possible example orderings in few-shot ICL and recommend the best order(s) by distinguishing between correct and incorrect outputs resulting from different order permutations. Through a detailed empirical evaluation on multiple LLMs, datasets and prompts, we demonstrate that OptiSeq improves accuracy by 6 - 10.5 percentage points across multiple tasks.

In this work, we focus our attention on developing a benchmark for instruction-following where it is easy to verify both task performance as well as instruction-following capabilities. We adapt existing knowledge benchmarks and augment them with instructions that are a) conditional on correctly answering the knowledge task or b) use the space of candidate options in multiple-choice knowledge-answering tasks. This allows us to study model characteristics, such as their change in performance on the knowledge tasks in the presence of answer-modifying instructions and distractor instructions. In contrast to existing benchmarks for instruction following, we not only measure instruction-following capabilities but also use LLM-free methods to study task performance. We study a series of openly available large language models of varying parameter sizes (1B-405B) and closed source models namely GPT-4o-mini, GPT-4o. We find that even large-scale instruction-tuned LLMs fail to follow simple instructions in zero-shot settings. We release our dataset, the benchmark, code, and results for future work.

Large language models (LLMs) have recently shown tremendous promise in serving as the backbone to agentic systems, as demonstrated by their performance in multi-faceted, challenging benchmarks like SWE-Bench and Agent-Bench. However, to realize the true potential of LLMs as autonomous agents, they must learn to identify, call, and interact with external tools and application program interfaces (APIs) to complete complex tasks. These tasks together are termed function calling. Endowing LLMs with function calling abilities leads to a myriad of advantages, such as access to current and domain-specific information in databases and knowledge sources, and the ability to outsource tasks that can be reliably performed by tools, e.g., a Python interpreter or calculator. While there has been significant progress in function calling with LLMs, there is still a dearth of open models that perform on par with proprietary LLMs like GPT, Claude, and Gemini. Therefore, in this work, we introduce the GRANITE-20B-FUNCTIONCALLING model under an Apache 2.0 license. The model is trained using a multi-task training approach on seven fundamental tasks encompassed in function calling, those being Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter-Value Pair Detection, Next-Best Function, and Response Generation. We present a comprehensive evaluation on multiple out-of-domain datasets comparing GRANITE-20B-FUNCTIONCALLING to more than 15 other best proprietary and open models. GRANITE-20B-FUNCTIONCALLING provides the best performance among all open models on the Berkeley Function Calling Leaderboard and fourth overall. As a result of the diverse tasks and datasets used for training our model, we show that GRANITE-20B-FUNCTIONCALLING has better generalizability on multiple tasks in seven different evaluation datasets.

There are increasingly many large language models (LLMs) available to the public. While these LLMs have exhibited impressive abilities on a variety of task, any individual LLM in particular may do well on some tasks and worse on others. Additionally, the performance of these models is heavily dependent on the choice of prompt template used. For instance, they exhibit sensitivity to the few shot examples chosen or brittleness to the wording of instructions. Moreover, a prompt template that makes a model perform well for one input may not be the optimal template for another input. This necessitates an approach for adaptively selecting LLM and prompt template pairs for each input. Recent work has shown that the accuracy of LLM's responses is correlated with the LLM's confidence in the response. Thus, a natural choice for selecting which model and prompt template to use is to select the pair that is most confident in its response. However, existing confidence metrics are expensive to calculate - necessitating multiple calls to each LLm and prompt pair. We thus propose an approach to predict the confidence of each pair using an auxiliary regression model that is inexpensive to run. Using this auxiliary model, we select the LLM and prompt template with the highest predicted confidence for a given input. Results on a range of benchmark datasets show that our confidence-based instance-level prompt search method consistently improves the performance of LLMs.

The inception of large language models has helped advance the state-of-the-art on numerous natural language tasks. This has also opened the door for the development of foundation models for other domains and data modalities (e.g., images and code). In this paper, we argue that business process data has unique characteristics that warrant the creation of a new class of foundation models to handle tasks like activity prediction, process optimization, and decision making. These models should also tackle the challenges of applying AI to business processes which include data scarcity, multi-modal representations, domain specific terminology, and privacy concerns. To support our claim, we show the effectiveness of few-shot learning and transfer learning in next activity prediction, crucial properties for the success of foundation models.