Related papers: Asking a Language Model for Diverse Responses

Question answer generation using Natural Language Processing models is ubiquitous in the world around us. It is used in many use cases such as the building of chat bots, suggestive prompts in google search and also as a way of navigating…

Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

We propose a method for natural language generation, choosing the most representative output rather than the most likely output. By viewing the language generation process from the voting theory perspective, we define representativeness…

Selecting high-quality and diverse training samples from extensive datasets plays a crucial role in reducing training overhead and enhancing the performance of Large Language Models (LLMs). However, existing studies fall short in assessing…

Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among…

Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-constrained settings. Existing approaches often depend on…

Recent advancements in large language models (LLMs) have shifted focus toward scaling inference-time compute, improving performance without retraining the model. A common approach is to sample multiple outputs in parallel, and select one of…

Large language models (LLMs) are known to produce outputs with limited diversity. In this work, we study whether infusing random concepts in the prompts can improve the diversity of the generated outputs. To benchmark the approach, we…

Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…

Today's probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the…

Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-based filtered expectation-maximization (FEM) objective for…

The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two…

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…

A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a response, which may result in homogenization of the responses,…

How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through…

Inference-time scaling via repeated sampling has shown promise in reasoning tasks, but its effectiveness in multilingual generation remains underexplored. We evaluate this approach using perplexity- and reward-based verifiers on two…

The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or…

Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information…

Synthetic users are cost-effective proxies for real users in the evaluation of conversational recommender systems. Large language models show promise in simulating human-like behavior, raising the question of their ability to represent a…