Prompting is the primary method by which we study and control large language models. It is also one of the most powerful: nearly every major capability attributed to LLMs--few-shot learning, chain-of-thought, constitutional AI--was first unlocked through prompting. Yet prompting is rarely treated as science and is frequently frowned upon as alchemy. We argue that this is a category error. If we treat LLMs as a new kind of organism--complex, opaque, and trained rather than programmed--then prompting is not a workaround.

Two narratives about machine learning ecosystems grew out of the recent algorithmic fairness discourse. In one, dubbed monoculture, algorithmic ecosystems tend toward homogeneity akin to a single model making all decisions. Individuals then face the risk of systematic exclusion with no recourse. In the other, model multiplicity, many models solve the same task with similar accuracy, causing excessive variation in individual outcomes. Both narratives are compelling, yet, seemingly at odds: model multiplicity can't materialize in a strict monoculture.

Recent advances in video generation models have sparked interest in world models capable of simulating realistic environments. While navigation has been wellexplored, physically meaningful interactions that mimic real-world forces remain largely understudied. In this work, we investigate using physical forces as a control signal for video generation and propose force prompts which enable users to interact with images through both localized point forces, such as poking a plant, and global wind force fields, such as wind blowing on fabric. We demonstrate that these force prompts can enable videos to respond realistically to physical control signals by leveraging the visual and motion prior in the original pretrained model, without using any 3D asset or physics simulator at inference. The primary challenge of force prompting is the difficulty in obtaining high quality paired force-video training data, both in the real world due to the difficulty of obtaining force signals, and in synthetic data due to limitations in the visual quality and domain diversity of physics simulators.

Large language models (LLMs) can learn to perform a wide range of natural language tasks from just a handful of in-context examples. However, for generating strings from highly structured languages (e.g., semantic parsing to complex domainspecific languages), it is challenging for the LLM to generalize from just a few exemplars. We propose grammar prompting, a simple approach to enable LLMs to use external knowledge and domain-specific constraints, expressed through a grammar in Backus-Naur Form (BNF), during in-context learning. Grammar prompting augments each demonstration example with a specialized grammar that is minimally sufficient for generating the particular output example, where the specialized grammar is a subset of the full DSL grammar. For inference, the LLM first predicts a BNF grammar given a test input, and then generates the output according to the rules of the grammar. Experiments demonstrate that grammar prompting can enable LLMs to perform competitively on a diverse set of DSL generation tasks, including semantic parsing (SMCalFlow, Overnight, GeoQuery), PDDL planning, and SMILES-based molecule generation.

The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nuanced ideas in text alone can be difficult.

This paper investigates an under-explored challenge in large language models (LLMs): chain-of-thought prompting with noisy rationales, which include irrelevant or inaccurate reasoning thoughts within examples used for in-context learning. We construct NoRa dataset that is tailored to evaluate the robustness of reasoning in the presence of noisy rationales. Our findings on NoRa dataset reveal a prevalent vulnerability to such noise among current LLMs, with existing robust methods like self-correction and self-consistency showing limited efficacy. Notably, compared to prompting with clean rationales, base LLM drops by 1.4%-19.8% in accuracy with irrelevant thoughts and more drastically by 2.2%-40.4% with inaccurate thoughts.Addressing this challenge necessitates external supervision that should be accessible in practice. Here, we propose the method of contrastive denoising with noisy chain-of-thought (CD-CoT). It enhances LLMs' denoising-reasoning capabilities by contrasting noisy rationales with only one clean rationale, which can be the minimal requirement for denoising-purpose prompting. This method follows a principle of exploration and exploitation: (1) rephrasing and selecting rationales in the input space to achieve explicit denoising and (2) exploring diverse reasoning paths and voting on answers in the output space. Empirically, CD-CoT demonstrates an average improvement of 17.8% in accuracy over the base model and shows significantly stronger denoising capabilities than baseline methods.

Hence, we consider asking a VLM to provide the scientific name of the organism shown in a given image. There are two types of questions that we consider for this task. First, we consider open-ended questions, where we do not provide any answer choices (or options) to the VLM in the input prompt.

Models (LLMs) can sometimes surpass those annotated by experts, such as journalists, according to human evaluations. However, there is limited research on whether these generic summaries meet the individual needs of ordinary people.

Section A.2 shows results using a chat-style verbalized numeric Section A.3 shows results on four extra benchmark tasks made available with Finally, Section A.5 presents and discusses results on feature In this section, we evaluate risk score calibration on the income prediction task across different subpopulations, such as typically done as part of a fairness audit. Figures A1-A2 show group-conditional calibration curves for all models on the ACSIncome task, evaluated on three subgroups specified by the race attribute in the ACS data. We show the three race categories with largest representation. The'Mixtral 8x22B' and'Yi 34B' models shown are the worst offenders, where samples belonging to the'Black' population see consistently lower scores for the same positive label probability when compared to the'Asian' or'White' populations. On average, the'Mixtral 8x22B (it)' model classifies a Black individual with a In fact, this score bias can be reversed for some base models, overestimating scores from Black individuals compared with other subgroups.