Related papers: PITA: Preference-Guided Inference-Time Alignment f…

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional…

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Current techniques for post-training Large Language Models (LLMs) rely either on costly human supervision or on external verifiers to boost performance on tasks such as mathematical reasoning and code generation. However, as LLMs improve…

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more cost-effective alternative is to fuse existing pre-trained…

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target…

Large language models (LLMs) are increasingly used to generate feedback, yet their impact on learning remains underexplored, especially compared to existing feedback methods. This study investigates how on-demand LLM-generated explanatory…

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. While efforts have been made to combine these…

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Large language models (LLMs) are revolutionizing conversational recommender systems by adeptly indexing item content, understanding complex conversational contexts, and generating relevant item titles. However, controlling the distribution…

Large Language Models (LLMs) are increasingly deployed across diverse applications that demand balancing multiple, often conflicting, objectives -- such as helpfulness, harmlessness, or humor. Many traditional methods for aligning outputs…

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

The rapid evolution of large language models (LLMs) has intensified the demand for effective personalization techniques that can adapt model behavior to individual user preferences. Despite the non-parametric methods utilizing the…

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

In sequential recommendation, models recommend items based on user's interaction history. To this end, current models usually incorporate information such as item descriptions and user intent or preferences. User preferences are usually not…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

Large language models (LLMs) have achieved remarkable success, yet aligning their generations with human preferences remains a critical challenge. Existing approaches to preference modeling often rely on an explicit or implicit reward…