paper-with-me

홈 › Papers

Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models

2023-10-25 · Xiang Chen, Xiaojun Wan

Advancements in natural language generation (NLG) and large language models (LLMs) have led to proficient text generation in various tasks. However, integrating intricate constraints into neural text generation, due to LLMs' opacity, remains challenging. This study investigates constrained text generation for LLMs, where predefined constraints are applied during LLM's generation process. Our research mainly focuses on mainstream open-source LLMs, categorizing constraints into lexical, structural, and relation-based types. We also present various benchmarks to facilitate fair evaluation. The study addresses some key research questions, including evaluating, understanding and improving constrained text generation for LLMs. Results illuminate LLMs' capacity and deficiency to incorporate constraints and provide insights for future developments in constrained text generation. Codes and datasets will be released upon acceptance.

📄 PDF Abstract BibTeX arXiv:2310.16343

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

2026-04-30 · Keming Wu, Zuhao Yang, Kaichen Zhang, Shizun Wang 외 arxiv

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consist…

Instruction FollowingSpatial Reasoning

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies

2024-04-08 · Xuanfan Ni, Hengyi Cai, Xiaochi Wei, Shuaiqiang Wang 외

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks but are constrained by their small context window sizes. Various efforts have been proposed to expand the context window to accom…

Long-Context UnderstandingReading Comprehension

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation

2023-11-26 · Xun Liang, Shichao Song, Simin Niu, Zhiyu Li 외

Large language models (LLMs) have emerged as pivotal contributors in contemporary natural language processing and are increasingly being applied across a diverse range of industries. However, these large-scale probabilis…

BenchmarkingHallucinationHallucination EvaluationText Generation

SRS-Stories: Vocabulary-constrained multilingual story generation for language learning

2025-12-20 · Wiktor Kamzela, Mateusz Lango, Ondrej Dusek arxiv

In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know. The generated texts are specifically written to teach the user new vocabulary by si…

Story Generation

Evaluating Structured Decoding for Text-to-Table Generation: Evidence from Three Datasets

2025-08-21 · Julian Oestreich, Lydia Müller arxiv

We present a comprehensive evaluation of structured decoding for text-to-table generation with large language models (LLMs). While previous work has primarily focused on unconstrained generation of tables, the impact of …