We present a new challenge to examine whether large language models understand social norms. In contrast to existing datasets, our dataset requires a fundamental understanding of social norms to solve. Our dataset features the largest set of social norm skills, consisting of 402 skills and 12,383 questions covering a wide set of social norms ranging from opinions and arguments to culture and laws. We design our dataset according to the K-12 curriculum. This enables the direct comparison of the social understanding of large language models to humans, more specifically, elementary students. While prior work generates nearly random accuracy on our benchmark, recent large language models such as GPT3.5-Turbo and LLaMA2-Chat are able to improve the performance significantly, only slightly below human performance. We then propose a multi-agent framework based on large language models to improve the models' ability to understand social norms. This method further improves large language models to be on par with humans. Given the increasing adoption of large language models in real-world applications, our finding is particularly important and presents a unique direction for future improvements.

Supervised fine-tuning (SFT) on instruction-following corpus is a crucial approach toward the alignment of large language models (LLMs). However, the performance of LLMs on standard knowledge and reasoning benchmarks tends to suffer from deterioration at the latter stage of the SFT process, echoing the phenomenon of alignment tax. Through our pilot study, we put a hypothesis that the data biases are probably one cause behind the phenomenon. To address the issue, we introduce a simple disperse-then-merge framework. To be concrete, we disperse the instruction-following data into portions and train multiple sub-models using different data portions. Then we merge multiple models into a single one via model merging techniques. Despite its simplicity, our framework outperforms various sophisticated methods such as data curation and training regularization on a series of standard knowledge and reasoning benchmarks.

We introduce a new challenge to test the STEM skills of neural models. The problems in the real world often require solutions, combining knowledge from STEM (science, technology, engineering, and math). Unlike existing datasets, our dataset requires the understanding of multimodal vision-language information of STEM. Our dataset features one of the largest and most comprehensive datasets for the challenge. It includes 448 skills and 1,073,146 questions spanning all STEM subjects. Compared to existing datasets that often focus on examining expert-level ability, our dataset includes fundamental skills and questions designed based on the K-12 curriculum. We also add state-of-the-art foundation models such as CLIP and GPT-3.5-Turbo to our benchmark. Results show that the recent model advances only help master a very limited number of lower grade-level skills (2.5% in the third grade) in our dataset. In fact, these models are still well below (averaging 54.7%) the performance of elementary students, not to mention near expert-level performance. To understand and increase the performance on our dataset, we teach the models on a training split of our dataset. Even though we observe improved performance, the model performance remains relatively low compared to average elementary students. To solve STEM problems, we will need novel algorithmic innovations from the community.

Amyotrophic lateral sclerosis (ALS) severely impairs patients' ability to communicate, often leading to a decline in their quality of life within a few years of diagnosis. The P300 speller brain-computer interface (BCI) offers an alternative communication method by interpreting a subject's EEG response to characters presented on a grid interface. This paper addresses the common speed limitations encountered in training efficient P300-based multi-subject classifiers by introducing innovative "across-subject" classifiers. We leverage a combination of the second-generation Generative Pre-Trained Transformer (GPT2) and Dijkstra's algorithm to optimize stimuli and suggest word completion choices based on typing history. Additionally, we employ a multi-layered smoothing technique to accommodate out-of-vocabulary (OOV) words. Through extensive simulations involving random sampling of EEG data from subjects, we demonstrate significant speed enhancements in typing passages containing rare and OOV words. These optimizations result in approximately 10% improvement in character-level typing speed and up to 40% improvement in multi-word prediction. We demonstrate that augmenting standard row/column highlighting techniques with layered word prediction yields close-to-optimal performance. Furthermore, we explore both "within-subject" and "across-subject" training techniques, showing that speed improvements are consistent across both approaches.

Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, especially in complex decision-making scenarios, but their static problem-solving strategies often limit their adaptability to dynamic environments. We explore the enhancement of reasoning capabilities in LLMs through Temperature Tree ($T^2$) prompting via Particle Swarm Optimization, termed as $T^2$ of Thoughts ($T^2oT$). The primary focus is on enhancing decision-making processes by dynamically adjusting search parameters, especially temperature, to improve accuracy without increasing computational demands. We empirically validate that our hybrid $T^2oT$ approach yields enhancements in, single-solution accuracy, multi-solution generation and text generation quality. Our findings suggest that while dynamic search depth adjustments based on temperature can yield mixed results, a fixed search depth, when coupled with adaptive capabilities of $T^2oT$, provides a more reliable and versatile problem-solving strategy. This work highlights the potential for future explorations in optimizing algorithmic interactions with foundational language models, particularly illustrated by our development for the Game of 24 and Creative Writing tasks.

This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditionally used solely for retrieval--as features from the retrieval modality. By employing a modality fusion methodology, xRAG seamlessly integrates these embeddings into the language model representation space, effectively eliminating the need for their textual counterparts and achieving an extreme compression rate. In xRAG, the only trainable component is the modality bridge, while both the retriever and the language model remain frozen. This design choice allows for the reuse of offline-constructed document embeddings and preserves the plug-and-play nature of retrieval augmentation. Experimental results demonstrate that xRAG achieves an average improvement of over 10% across six knowledge-intensive tasks, adaptable to various language model backbones, ranging from a dense 7B model to an 8x7B Mixture of Experts configuration. xRAG not only significantly outperforms previous context compression methods but also matches the performance of uncompressed models on several datasets, while reducing overall FLOPs by a factor of 3.53. Our work pioneers new directions in retrieval-augmented generation from the perspective of multimodality fusion, and we hope it lays the foundation for future efficient and scalable retrieval-augmented systems

Large language models (LLMs) store extensive factual knowledge, but the mechanisms behind how they store and express this knowledge remain unclear. The Knowledge Neuron (KN) thesis is a prominent theory for explaining these mechanisms. This theory is based on the knowledge localization (KL) assumption, which suggests that a fact can be localized to a few knowledge storage units, namely knowledge neurons. However, this assumption may be overly strong regarding knowledge storage and neglects knowledge expression mechanisms. Thus, we re-examine the KL assumption and confirm the existence of facts that do not adhere to it from both statistical and knowledge modification perspectives. Furthermore, we propose the Query Localization (QL) assumption. (1) Query-KN Mapping: The localization results are associated with the query rather than the fact. (2) Dynamic KN Selection: The attention module contributes to the selection of KNs for answering a query. Based on this, we further propose the Consistency-Aware KN modification method, which improves the performance of knowledge modification. We conduct 39 sets of experiments, along with additional visualization experiments, to rigorously validate our conclusions.

With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness-the semantic coherence of generated images to the prompts they were conditioned on. A variety of T2I faithfulness metrics have been proposed, leveraging advances in cross-modal embeddings and vision-language models (VLMs). However, these metrics are not rigorously compared and benchmarked, instead presented with correlation to human Likert scores over a set of easy-to-discriminate images against seemingly weak baselines. We introduce T2IScoreScore (TS2), a curated set of semantic error graphs containing a prompt and a set increasingly erroneous images. These allow us to rigorously judge whether a given prompt faithfulness metric can correctly order images with respect to their objective error count and significantly discriminate between different error nodes, using meta-metric scores derived from established statistical tests. Surprisingly, we find that the state-of-the-art VLM-based metrics (e.g., TIFA, DSG, LLMScore, VIEScore) we tested fail to significantly outperform simple (and supposedly worse) feature-based metrics like CLIPScore, particularly on a hard subset of naturally-occurring T2I model errors. TS2 will enable the development of better T2I prompt faithfulness metrics through more rigorous comparison of their conformity to expected orderings and separations under objective criteria.

Modern code review is a process in which an incremental code contribution made by a code author is reviewed by one or more peers before it is committed to the version control system. An important element of modern code review is verifying that code contributions adhere to best practices. While some of these best practices can be automatically verified, verifying others is commonly left to human reviewers. This paper reports on the development, deployment, and evaluation of AutoCommenter, a system backed by a large language model that automatically learns and enforces coding best practices. We implemented AutoCommenter for four programming languages (C++, Java, Python, and Go) and evaluated its performance and adoption in a large industrial setting. Our evaluation shows that an end-to-end system for learning and enforcing coding best practices is feasible and has a positive impact on the developer workflow. Additionally, this paper reports on the challenges associated with deploying such a system to tens of thousands of developers and the corresponding lessons learned.

Causal structure discovery from observations can be improved by integrating background knowledge provided by an expert to reduce the hypothesis space. Recently, Large Language Models (LLMs) have begun to be considered as sources of prior information given the low cost of querying them relative to a human expert. In this work, firstly, we propose a set of metrics for assessing LLM judgments for causal graph discovery independently of the downstream algorithm. Secondly, we systematically study a set of prompting designs that allows the model to specify priors about the structure of the causal graph. Finally, we present a general methodology for the integration of LLM priors in graph discovery algorithms, finding that they help improve performance on common-sense benchmarks and especially when used for assessing edge directionality. Our work highlights the potential as well as the shortcomings of the use of LLMs in this problem space.