We introduce Planning-guided Retrieval Augmented Generation (Plan$\times$RAG), a novel framework that augments the \emph{retrieve-then-reason} paradigm of existing RAG frameworks to \emph{plan-then-retrieve}. Plan$\times$RAG formulates a reasoning plan as a directed acyclic graph (DAG), decomposing queries into interrelated atomic sub-queries. Answer generation follows the DAG structure, allowing significant gains in efficiency through parallelized retrieval and generation. While state-of-the-art RAG solutions require extensive data generation and fine-tuning of language models (LMs), Plan$\times$RAG incorporates frozen LMs as plug-and-play experts to generate high-quality answers. Compared to existing RAG solutions, Plan$\times$RAG demonstrates significant improvements in reducing hallucinations and bolstering attribution due to its structured sub-query decomposition. Overall, Plan$\times$RAG offers a new perspective on integrating external knowledge in LMs while ensuring attribution by design, contributing towards more reliable LM-based systems.

For text-based AI systems to interact in the real world, causal reasoning is an essential skill. Since interventional data is costly to generate, we study to what extent an agent can learn causal reasoning from passive data. Specifically, we consider an axiomatic training setup where an agent learns from multiple demonstrations of a causal axiom (or rule), rather than incorporating the axiom as an inductive bias or inferring it from data values. A key question is whether the agent would learn to generalize from the axiom demonstrations to new scenarios. For example, if a transformer model is trained on demonstrations of the causal transitivity axiom over small graphs, would it generalize to applying the transitivity axiom over large graphs? Our results, based on a novel axiomatic training scheme, indicate that such generalization is possible. We consider the task of inferring whether a variable causes another variable, given a causal graph structure. We find that a 67 million parameter transformer model, when trained on linear causal chains (along with some noisy variations) can generalize well to new kinds of graphs, including longer causal chains, causal chains with reversed order, and graphs with branching; even when it is not explicitly trained for such settings. Our model performs at par (or even better) than many larger language models such as GPT-4, Gemini Pro, and Phi-3. Overall, our axiomatic training framework provides a new paradigm of learning causal reasoning from passive data that can be used to learn arbitrary axioms, as long as sufficient demonstrations can be generated.

Given an input query, a recommendation model is trained using user feedback data (e.g., click data) to output a ranked list of items. In real-world systems, besides accuracy, an important consideration for a new model is novelty of its top-k recommendations w.r.t. an existing deployed model. However, novelty of top-k items is a difficult goal to optimize a model for, since it involves a non-differentiable sorting operation on the model's predictions. Moreover, novel items, by definition, do not have any user feedback data. Given the semantic capabilities of large language models, we address these problems using a reinforcement learning (RL) formulation where large language models provide feedback for the novel items. However, given millions of candidate items, the sample complexity of a standard RL algorithm can be prohibitively high. To reduce sample complexity, we reduce the top-k list reward to a set of item-wise rewards and reformulate the state space to consist of tuples such that the action space is reduced to a binary decision; and show that this reformulation results in a significantly lower complexity when the number of items is large. We evaluate the proposed algorithm on improving novelty for a query-ad recommendation task on a large-scale search engine. Compared to supervised finetuning on recent pairs, the proposed RL-based algorithm leads to significant novelty gains with minimal loss in recall. We obtain similar results on the ORCAS query-webpage matching dataset and a product recommendation dataset based on Amazon reviews.

Given a task in the form of a basic description and its training examples, prompt optimization is the problem of synthesizing the given information into a text prompt for a large language model (LLM). Humans solve this problem by also considering the different facets that define a task (e.g., counter-examples, explanations, analogies) and including them in the prompt. However, it is unclear whether existing algorithmic approaches, based on iteratively editing a given prompt or automatically selecting a few in-context examples, can cover the multiple facets required to solve a complex task. In this work, we view prompt optimization as that of learning multiple facets of a task from a set of training examples. We identify and exploit structure in the prompt optimization problem -- first, we find that prompts can be broken down into loosely coupled semantic sections that have a relatively independent effect on the prompt's performance; second, we cluster the input space and use clustered batches so that the optimization procedure can learn the different facets of a task across batches. The resulting algorithm, UniPrompt, consists of a generative model to generate initial candidates for each prompt section; and a feedback mechanism that aggregates suggested edits from multiple mini-batches into a conceptual description for the section. Empirical evaluation on multiple datasets and a real-world task shows that prompts generated using UniPrompt obtain higher accuracy than human-tuned prompts and those from state-of-the-art methods. In particular, our algorithm can generate long, complex prompts that existing methods are unable to generate. Code for UniPrompt will be available at \url{https://aka.ms/uniprompt}.

This paper presents a comparative analysis of total cost of ownership (TCO) and performance between domain-adapted large language models (LLM) and state-of-the-art (SoTA) LLMs , with a particular emphasis on tasks related to coding assistance for chip design. We examine the TCO and performance metrics of a domain-adaptive LLM, ChipNeMo, against two leading LLMs, Claude 3 Opus and ChatGPT-4 Turbo, to assess their efficacy in chip design coding generation. Through a detailed evaluation of the accuracy of the model, training methodologies, and operational expenditures, this study aims to provide stakeholders with critical information to select the most economically viable and performance-efficient solutions for their specific needs. Our results underscore the benefits of employing domain-adapted models, such as ChipNeMo, that demonstrate improved performance at significantly reduced costs compared to their general-purpose counterparts. In particular, we reveal the potential of domain-adapted LLMs to decrease TCO by approximately 90%-95%, with the cost advantages becoming increasingly evident as the deployment scale expands. With expansion of deployment, the cost benefits of ChipNeMo become more pronounced, making domain-adaptive LLMs an attractive option for organizations with substantial coding needs supported by LLMs

The effective management of brain tumors relies on precise typing, subtyping, and grading. This study advances patient care with findings from rigorous multiple instance learning experimentations across various feature extractors and aggregators in brain tumor histopathology. It establishes new performance benchmarks in glioma subtype classification across multiple datasets, including a novel dataset focused on the Indian demographic (IPD- Brain), providing a valuable resource for existing research. Using a ResNet-50, pretrained on histopathology datasets for feature extraction, combined with the Double-Tier Feature Distillation (DTFD) feature aggregator, our approach achieves state-of-the-art AUCs of 88.08 on IPD-Brain and 95.81 on the TCGA-Brain dataset, respectively, for three-way glioma subtype classification. Moreover, it establishes new benchmarks in grading and detecting IHC molecular biomarkers (IDH1R132H, TP53, ATRX, Ki-67) through H&E stained whole slide images for the IPD-Brain dataset. The work also highlights a significant correlation between the model decision-making processes and the diagnostic reasoning of pathologists, underscoring its capability to mimic professional diagnostic procedures.

Recent works have shown that large language models (LLMs) work remarkably well on a wide range of tasks through in-context learning and optimization of in-context examples (ICE). However, most of these studies assume either a fixed or no instruction provided in the prompt, leading to the apparent consensus that the optimization of in-context examples is critical for better performance. We challenge this consensus for instruction-tuned LLMs by investigating the necessity of optimizing in-context examples when task-specific instructions are provided, and find that there are tasks for which various ways of optimizing in-context examples yield diminishing returns. We introduce a task-specific metric called \metriclong{} (\metric) that quantifies the learnability of tasks from a given instruction, and provides a heuristic that helps decide whether to optimize for instructions or ICE for any new task. On a wide range of tasks and a systematically created instruction set with gradually added details, we validate our hypothesis empirically by computing \metric with query-dependent bins of examples, comparing different instructions with ICE selection methods, and performing label perturbation experiments. We conclude that tasks can be divided into two broad classes based on the \metric metric, where the returns on ICE optimization follow predictable trends when instructions are provided in the prompt.

In many classification datasets, the task labels are spuriously correlated with some input attributes. Classifiers trained on such datasets often rely on these attributes for prediction, especially when the spurious correlation is high, and thus fail to generalize whenever there is a shift in the attributes' correlation at deployment. If we assume that the spurious attributes are known a priori, several methods have been proposed to learn a classifier that is invariant to the specified attributes. However, in real-world data, information about spurious attributes is typically unavailable. Therefore, we propose a method to automatically identify spurious attributes by estimating their causal effect on the label and then use a regularization objective to mitigate the classifier's reliance on them. Compared to a recent method for identifying spurious attributes, we find that our method is more accurate in removing the attribute from the learned model, especially when spurious correlation is high. Specifically, across synthetic, semi-synthetic, and real-world datasets, our method shows significant improvement in a metric used to quantify the dependence of a classifier on spurious attributes ($\Delta$Prob), while obtaining better or similar accuracy. In addition, our method mitigates the reliance on spurious attributes even under noisy estimation of causal effects. To explain the empirical robustness of our method, we create a simple linear classification task with two sets of attributes: causal and spurious. We prove that our method only requires that the ranking of estimated causal effects is correct across attributes to select the correct classifier.

Several scientific communities are currently facing a replication crisis, wherein it has proven difficult or impossible for researchers to independently verify the results of previously published studies. Failures to replicate large swaths of experimental work (Camerer et al., 2018; Nosek et al., 2015; Begley and Ellis, 2012; Baker, 2016) have come in fields like psychology or medicine, that focus on what Hofman et al. (2021) call explanatory modeling, where the goal is to identify and estimate causal effects (e.g., is there an effect of X on Y, and if so, how large is it?). While there are many different factors that can contribute to unreliable findings in explanatory modeling, the combination of small-scale experiments involving noisy measurements and the (mis)use of null hypothesis significance testing (NHST) has received a great deal of attention in recent years. Under these conditions, researchers can mistake idiosyncratic patterns in noise for true effects, resulting in unreliable findings that do not replicate upon further investigation (Button et al., 2013; Loken and Gelman, 2017; Meehl, 1990; Simmons et al., 2011). More generally, some forms of data-dependent decision making (e.g., about how to define research questions or hypotheses, how to filter or transform data, how to model data, what tests to run, etc.) can lead to similar problems regardless of the specifics of the methods (Gelman and Loken, 2013). What about other fields, such as machine learning and data science, that focus less on explanation and more on predictive modeling, defined in Hofman et al. (2021) as directly forecasting outcomes (e.g., how well can an outcome Y be predicted using all available features X?) without necessarily focusing on isolating individual causal effects? Predictive modeling is typically done by testing (out-of-sample) predictions on large-scale datasets, and hence--unlike explanatory modeling--involves neither small experiments nor misuse of significance testing. With advances in the fields of statistics and machine learning (ML) we have seen remarkable performance gains in predictive modeling over the last decade, for both traditional ML tasks and for scientific applications. The same methods that have been shown to achieve at or above human-level performance on tasks like playing chess, classifying images, or understanding natural language (Zhang et al.,

Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In this paper, we address model-agnostic explanations, proposing two approaches for counterfactual (CF) approximation. The first approach is CF generation, where a large language model (LLM) is prompted to change a specific text concept while keeping confounding concepts unchanged. While this approach is demonstrated to be very effective, applying LLM at inference-time is costly. We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space. This space is faithful to a given causal graph and effectively serves to identify matches that approximate CFs. After showing theoretically that approximating CFs is required in order to construct faithful explanations, we benchmark our approaches and explain several models, including LLMs with billions of parameters. Our empirical results demonstrate the excellent performance of CF generation models as model-agnostic explainers. Moreover, our matching approach, which requires far less test-time resources, also provides effective explanations, surpassing many baselines. We also find that Top-K techniques universally improve every tested method. Finally, we showcase the potential of LLMs in constructing new benchmarks for model explanation and subsequently validate our conclusions. Our work illuminates new pathways for efficient and accurate approaches to interpreting NLP systems.