Related papers: ECO Decoding: Entropy-Based Control for Controllab…

Conformal Prediction (CP) is a powerful framework for constructing prediction sets with guaranteed coverage. However, recent studies have shown that integrating confidence calibration with CP can lead to a degradation in efficiency. In this…

While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a…

Generative control policies have recently unlocked major progress in robotics. These methods produce action sequences via diffusion or flow matching, with training data provided by demonstrations. But existing methods come with two key…

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a sequence-level verifier. It can thus be viewed as sampling…

Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial…

Difficulty-controllable question generation for reading comprehension has gained significant attention in the field of education as a fundamental tool for adaptive learning support. Although several neural question generation methods have…

Despite great advances, achieving high-fidelity emotional voice conversion (EVC) with flexible and interpretable control remains challenging. This paper introduces ClapFM-EVC, a novel EVC framework capable of generating high-quality…

In recent years, there has been a growing interest in the development of language models capable of generating text with controllable attributes. While several approaches have been proposed, many of these methods require condition-specific…

Achieving empathy is a crucial step toward humanized dialogue systems. Current approaches for empathetic dialogue generation mainly perceive an emotional label to generate an empathetic response conditioned on it, which simply treat…

Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and onset and offset timestamps. This enables precise control…

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many…

Multi-aspect controllable text generation is a more challenging and practical task than single-aspect control. Existing methods achieve complex multi-aspect control by fusing multiple controllers learned from single-aspect, but suffer from…

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time…

Controlled text generation techniques aim to regulate specific attributes (e.g. sentiment) while preserving the attribute independent content. The state-of-the-art approaches model the specified attribute as a structured or discrete…

Controllable speech generation methods typically rely on single or fixed prompts, hindering creativity and flexibility. These limitations make it difficult to meet specific user needs in certain scenarios, such as adjusting the style while…

We address the problem of human-in-the-loop control for generating prosody in the context of text-to-speech synthesis. Controlling prosody is challenging because existing generative models lack an efficient interface through which users can…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

Grounding external knowledge can enhance the factuality of responses in dialogue generation. However, excessive emphasis on it might result in the lack of engaging and diverse expressions. Through the introduction of randomness in sampling,…