Related papers: CHOIR: Collaborative Harmonization fOr Inference R…

Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative REAsoner (COREA), a system that cascades an SLM with an LLM to…

Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and…

Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. However, in many reasoning domains, the model must also validate generated tasks and…

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF). Unlike humans, whose…

Modern organizations frequently rely on chat-based platforms (e.g., Slack, Microsoft Teams, and Discord) for day-to-day communication and decision-making. As conversations evolve, organizational knowledge can get buried, prompting repeated…

Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule, which focuses on the most frequent answer while…

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

Large language models (LLMs) struggle with compositional generalisation, limiting their ability to systematically combine learned components to interpret novel inputs. While architectural modifications, fine-tuning, and data augmentation…

Different large language models (LLMs) exhibit diverse strengths and weaknesses, and LLM ensemble serves as a promising approach to integrate their complementary capabilities. Despite substantial progress in improving ensemble quality,…

To facilitate robust and trustworthy deployment of large language models (LLMs), it is essential to quantify the reliability of their generations through uncertainty estimation. While recent efforts have made significant advancements by…

Large language models require consistent behavioral patterns for safe deployment, yet there are indications of large variability that may lead to an instable expression of personality traits in these models. We present PERSIST (PERsonality…

Very large language models (LLMs) such as GPT-4 have shown the ability to handle complex tasks by generating and self-refining step-by-step rationales. Smaller language models (SLMs), typically with < 13B parameters, have been improved by…

Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM families (12…

Music Information Retrieval (MIR) encompasses a broad range of computational techniques for analyzing and understanding musical content, with recent deep learning advances driving substantial improvements. Building upon these advances, this…

Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advances in reasoning capabilities have significantly enhanced…

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified…

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We…

Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model. However, existing designs suffers in performance due to misalignment between training…