Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration

MIT（麻省理工学院）

Fan-Keng Sun, Cheng-I Lai

英文摘要：

Transformer-based language models have shown to be very powerful for natural language generation (NLG). However, text generation conditioned on some user inputs, such as topics or attributes, is non-trivial. Past approach relies on either modifying the original LM architecture, re-training the LM on corpora with attribute labels, or having separately trained `guidance models' to guide text generation in decoding. We argued that the above approaches are not necessary, and the original unconditioned LM is sufficient for conditioned NLG. We evaluated our approaches by the samples' fluency and diversity with automated and human evaluation.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

基于非对称强化学习与自蒸馏的指令条件探索

Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy

University of Southampton（南安普顿大学）

该研究针对LLM强化学习中的探索挑战，提出指令条件探索（ICE）方法，结合非对称RL/SD训练目标，使Qwen3-1.7B数学推理性能提升5.0%且长上下文下仍有效。

2026-08-06cs.AIcs.CLcs.LG

Revisiting Challenges in Data-to-Text Generation with Fact Grounding

University of California Santa Barbara（加州大学圣巴巴拉分校）

Data-to-text generation models face challenges in ensuring data fidelity by referring to the correct input source. To inspire studies in this area, Wiseman et al. (2017) introduced the RotoWire corpus on generating NBA game summaries from the box- and line-score tables. However, limited attempts have been made in this direction and the challenges remain. We observe a prominent bottleneck in the corpus where only about 60% of the summary contents can be grounded to the boxscore records. Such information deficiency tends to misguide a conditioned language model to produce unconditioned random fa…

2020-01-12cs.CL

自动诗歌生成中的多样性评估

Evaluating Diversity in Automatic Poetry Generation

University of Mannheim（曼海姆大学）；University of Technology Nuremberg (UTN)（纽伦堡工业大学（UTN））；Bielefeld University（比勒费尔德大学）

本研究评估自动诗歌生成（四行诗）的多样性，比较生成与人类诗歌在结构、词汇、语义和文体上的分布，发现现有系统多样性不足，而文体条件化和字符级建模能显著提升多样性。

2024-11-08cs.CL

高效推理探索：基于状态条件潜在引导与进度指导

Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance

The University of Hong Kong（香港大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Arizona State University（亚利桑那州立大学）；Simon Fraser University（西蒙弗雷泽大学）；The University of Manchester（曼彻斯特大学）；Tencent（腾讯）

提出SPS框架，通过状态条件潜在引导和进度指导，解决推理模型探索崩溃问题，提升探索效率，实验证明优于强基线。

2026-10-12cs.CL

GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion

Alexa AI（Alexa人工智能）

In this paper, we propose GlowVC: a multilingual multi-speaker flow-based model for language-independent text-free voice conversion. We build on Glow-TTS, which provides an architecture that enables use of linguistic features during training without the necessity of using them for VC inference. We consider two versions of our model: GlowVC-conditional and GlowVC-explicit. GlowVC-conditional models the distribution of mel-spectrograms with speaker-conditioned flow and disentangles the mel-spectrogram space into content- and pitch-relevant dimensions, while GlowVC-explicit models the explicit di…

2022-07-04cs.CLcs.LGeess.AS

自行调用邻居：带目标条件的同策略自蒸馏图游走

Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation

School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）；The University of Queensland（昆士兰大学）

该研究针对文本属性图推理中邻居固定的问题，提出CNY框架，结合目标条件同策略自蒸馏，使LLMs主动探索邻居，在基准实验中表现优于基线且策略可迁移。

2026-09-01cs.AIcs.CL