We look at reasoning on GSM8k, a dataset of short texts presenting primary school, math problems. We find, with Mirzadeh et al. (2024), that current LLM progress on the data set may not be explained by better reasoning but by exposure to a broader pretraining data distribution. We then introduce a novel information source for helping models with less data or inferior training reason better: discourse structure. We show that discourse structure improves performance for models like Llama2 13b by up to 160%. Even for models that have most likely memorized the data set, adding discourse structural information to the model still improves predictions and dramatically improves large model performance on out of distribution examples.

Query-focused tabular summarization is an emerging task in table-to-text generation that synthesizes a summary response from tabular data based on user queries. Traditional transformer-based approaches face challenges due to token limitations and the complexity of reasoning over large tables. To address these challenges, we introduce DETQUS (Decomposition-Enhanced Transformers for QUery-focused Summarization), a system designed to improve summarization accuracy by leveraging tabular decomposition alongside a fine-tuned encoder-decoder model. DETQUS employs a large language model to selectively reduce table size, retaining only query-relevant columns while preserving essential information. This strategy enables more efficient processing of large tables and enhances summary quality. Our approach, equipped with table-based QA model Omnitab, achieves a ROUGE-L score of 0.4437, outperforming the previous state-of-the-art REFACTOR model (ROUGE-L: 0.422). These results highlight DETQUS as a scalable and effective solution for query-focused tabular summarization, offering a structured alternative to more complex architectures.

The rapid advancement of large language models (LLMs) and artificial intelligence-generated content (AIGC) has accelerated AI-native applications, such as AI-based storybooks that automate engaging story production for children. However, challenges remain in improving story attractiveness, enriching storytelling expressiveness, and developing open-source evaluation benchmarks and frameworks. Therefore, we propose and opensource MM-StoryAgent, which creates immersive narrated video storybooks with refined plots, role-consistent images, and multi-channel audio. MM-StoryAgent designs a multi-agent framework that employs LLMs and diverse expert tools (generative models and APIs) across several modalities to produce expressive storytelling videos. The framework enhances story attractiveness through a multi-stage writing pipeline. In addition, it improves the immersive storytelling experience by integrating sound effects with visual, music and narrative assets. MM-StoryAgent offers a flexible, open-source platform for further development, where generative modules can be substituted. Both objective and subjective evaluation regarding textual story quality and alignment between modalities validate the effectiveness of our proposed MM-StoryAgent system. The demo and source code are available.

Multimodal Large Language Models (MLLMs) have garnered significant attention for their strong visual-semantic understanding. Most existing chart benchmarks evaluate MLLMs' ability to parse information from charts to answer questions. However, they overlook the inherent output biases of MLLMs, where models rely on their parametric memory to answer questions rather than genuinely understanding the chart content. To address this limitation, we introduce a novel Chart Hypothetical Question Answering (HQA) task, which imposes assumptions on the same question to compel models to engage in counterfactual reasoning based on the chart content. Furthermore, we introduce HAI, a human-AI interactive data synthesis approach that leverages the efficient text-editing capabilities of LLMs alongside human expert knowledge to generate diverse and high-quality HQA data at a low cost. Using HAI, we construct Chart-HQA, a challenging benchmark synthesized from publicly available data sources. Evaluation results on 18 MLLMs of varying model sizes reveal that current models face significant generalization challenges and exhibit imbalanced reasoning performance on the HQA task.

This study explores the use of OpenAI's API for inductive thematic analysis, employing a stepwise strategy to enhance transparency and traceability in GenAI-generated coding. A five-phase analysis and evaluation process were followed. Using the stepwise prompt, GenAI effectively generated codes with supporting statements and references, categorized themes, and developed broader interpretations by linking them to real-world contexts. While GenAI performed at a comparable level to human coders in coding and theming, it exhibited a more generalized and conceptual approach to interpretation, whereas human coders provided more specific, theme-based interpretations. Mapping these processes onto Naeem et al.'s (2023) six-step thematic analysis framework, GenAI covered four out of the six steps, while human coders followed three steps. Although GenAI's coding, theming, and interpretation align with keywording, coding, theming, and interpretation in Naeem et al.'s framework, human coders' interpretations were more closely tied to themes rather than broader conceptualization. This study positions GenAI as a viable tool for conducting inductive thematic analysis with minimal human intervention, offering an efficient and structured approach to qualitative data analysis. Future research should explore the development of specialized prompts that align GenAI's inductive thematic analysis with established qualitative research frameworks.

Routing large language models (LLMs) is a novel paradigm that recommends the most suitable LLM from a pool of candidates to process a given input through a well-designed router. Our comprehensive analysis reveals a model-level scaling-up phenomenon in LLMs, i.e., a capable router can significantly enhance the performance of this paradigm as the number of candidates increases. This improvement can even easily surpass the performance of the best single model in the pool and most existing strong LLMs, making it a highly promising paradigm. However, the lack of comprehensive and open-source benchmarks for Routing LLMs has hindered the development of routers. In this paper, we introduce RouterEval, a benchmark designed specifically for router research, which includes over 200,000,000 performance records for 12 popular LLM evaluations across areas such as knowledge-based Q&A, commonsense reasoning, semantic understanding, mathematical reasoning, and instruction following, based on more than 8,500 LLMs. Using RouterEval, extensive evaluations of existing Routing LLM methods reveal that most still have significant room for improvement. See https://github.com/MilkThink-Lab/RouterEval for all data, code, and tutorials.

When users formulate queries, they often include not only the information they seek, but also pragmatic markers such as interrogative phrasing or polite requests. Although these speech act indicators communicate the user\textquotesingle s intent -- whether it is asking a question, making a request, or stating a fact -- they do not necessarily add to the core informational content of the query itself. This paper investigates whether extracting the underlying propositional content from user utterances -- essentially stripping away the linguistic markers of intent -- can improve retrieval quality in Retrieval-Augmented Generation (RAG) systems. Drawing upon foundational insights from speech act theory, we propose a practical method for automatically transforming queries into their propositional equivalents before embedding. To assess the efficacy of this approach, we conducted an experimental study involving 63 user queries related to a Brazilian telecommunications news corpus with precomputed semantic embeddings. Results demonstrate clear improvements in semantic similarity between query embeddings and document embeddings at top ranks, confirming that queries stripped of speech act indicators more effectively retrieve relevant content.

Survey research is essential in energy demand studies for capturing consumer preferences and informing policy decisions. Stated preference (SP) surveys, in particular, analyse how individuals make trade-offs in hypothetical scenarios. However, traditional survey methods are costly, time-consuming, and affected by biases and respondent fatigue. Large language models (LLMs) have emerged as a potential tool to address these challenges by generating human-like textual responses. This study investigates the ability of LLMs to simulate consumer choices in energy-related SP surveys. A series of test scenarios evaluated the simulation performance of LLMs at both individual and aggregated levels, considering factors in the prompt, in-context learning (ICL), chain-of-thought (CoT) reasoning, the comparison between local and cloud-based LLMs, integration with traditional choice models, and potential biases. Results indicate that while LLMs achieve an average accuracy of up to 48%, surpassing random guessing, their performance remains insufficient for practical application. Local and cloud-based LLMs perform similarly in simulation accuracy but exhibit differences in adherence to prompt requirements and susceptibility to social desirability biases. Findings suggest that previous SP choices are the most effective input factor, while longer prompts with varied factor formats may reduce accuracy. Furthermore, the traditional mixed logit choice model outperforms LLMs and provides insights for refining LLM prompts. Despite their limitations, LLMs provide scalability and efficiency advantages, requiring minimal historical data compared to traditional survey methods. Future research should refine prompt structures, further investigate CoT reasoning, and explore fine-tuning techniques to improve LLM-based energy survey simulations.

The recent leap in AI capabilities, driven by big generative models, has sparked the possibility of achieving Artificial General Intelligence (AGI) and further triggered discussions on Artificial Superintelligence (ASI), a system surpassing all humans across all domains. This gives rise to the critical research question of: If we realize ASI, how do we align it with human values, ensuring it benefits rather than harms human society, a.k.a., the Superalignment problem. Despite ASI being regarded by many as solely a hypothetical concept, in this paper, we argue that superalignment is achievable and research on it should advance immediately, through simultaneous and alternating optimization of task competence and value conformity. We posit that superalignment is not merely a safeguard for ASI but also necessary for its realization. To support this position, we first provide a formal definition of superalignment rooted in the gap between capability and capacity and elaborate on our argument. Then we review existing paradigms, explore their interconnections and limitations, and illustrate a potential path to superalignment centered on two fundamental principles. We hope this work sheds light on a practical approach for developing the value-aligned next-generation AI, garnering greater benefits and reducing potential harms for humanity.

The quantization of large language models (LLMs) is crucial for deploying them on devices with limited computational resources. While advanced quantization algorithms offer improved performance compared to the basic linear quantization, they typically require high-end graphics processing units (GPUs), are often restricted to specific deep neural network (DNN) frameworks, and require calibration datasets. This limitation poses challenges for using such algorithms on various neural processing units (NPUs) and edge AI devices, which have diverse model formats and frameworks. In this paper, we show SplitQuantV2, an innovative algorithm designed to enhance low-bit linear quantization of LLMs, can achieve results comparable to those of advanced algorithms. SplitQuantV2 preprocesses models by splitting linear and convolution layers into functionally equivalent, quantization-friendly structures. The algorithm's platform-agnostic, concise, and efficient nature allows for implementation without the need for GPUs. Our evaluation on the Llama 3.2 1B Instruct model using the AI2's Reasoning Challenge (ARC) dataset demonstrates that SplitQuantV2 improves the accuracy of the INT4 quantization model by 11.76%p, matching the performance of the original floating-point model. Remarkably, SplitQuantV2 took only 2 minutes 6 seconds to preprocess the 1B model and perform linear INT4 quantization using only an Apple M4 CPU. SplitQuantV2 provides a practical solution for low-bit quantization on LLMs, especially when complex, computation-intensive algorithms are inaccessible due to hardware limitations or framework incompatibilities.