Related papers: Self-Control of LLM Behaviors by Compressing Suffi…

Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective…

Prompt engineering has emerged as a powerful technique for optimizing large language models (LLMs) for specific applications, enabling faster prototyping and improved performance, and giving rise to the interest of the community in…

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Effective collaboration requires groups to strategically regulate themselves to overcome challenges. Research has shown that groups may fail to regulate due to differences in members' perceptions of challenges which may benefit from…

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…

Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their behavior. This suggests a limited degree of metacognition -…

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting starting only from unlabeled seed questions with no ground-truth…

Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach…

In this paper, we propose a simple yet efficient approach based on prompt engineering that leverages the large language model itself to optimize its answers without relying on auxiliary models. We introduce an iterative self-evaluating…

This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. Multi-modal LLMs empower multi-modality understanding with the capability of semantic generation yet bring less…

The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yielding privacy risks for both model and data owners. One…

Despite the remarkable reasoning performance, eliciting the long chain-of-thought (CoT) ability in large language models (LLMs) typically requires costly reinforcement learning or supervised fine-tuning on high-quality distilled data. We…

Mastering a skill generally relies on both hands-on experience from doers and insightful, high-level guidance by mentors. Will this strategy also work well for solving complex non-convex optimization problems? Here, a common gradient-based…

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid such distortions. Yet, across 72 experiments and ~41,000 queries, we discovered massive…

Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammars (CFGs) in guaranteeing generation validity. However, such…

Providing Language Models (LMs) with relevant evidence in the context (either via retrieval or user-provided) can significantly improve their ability to provide better-grounded responses. However, recent studies have found that LMs often…

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…