Challenge: Recent advances in large language models have improved their capacity to handle long text inputs, but current models still exhibit unsatisfactory performance in long-form generation.
Approach: They propose a method to enhance long-form text generation through step-level supervision by leveraging Monte Carlo Tree Search to collect stepwise preference pairs and employ a global memory pool to maintain factual accuracy.
Outcome: The proposed method improves performance on long-form generation benchmarks while maintaining lossless performance on several general benchmarks.

Similar Papers

LoGU: Long-form Generation with Uncertainty Expressions (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate factually incorrect content, i.e., hallucinations, despite impressive performance.
Approach: They propose a framework to enable models to express uncertainty when unsure . they propose atomic claims to refine uncertainty and refine it using supervised fine-tuning and direct preference optimization to enhance uncertainty expression.
Outcome: The proposed framework significantly improves accuracy, reduces hallucinations, and maintains comprehensiveness of responses.
PIC: Unlocking Long-Form Text Generation Capabilities of Large Language Models via Position ID Compression (2025.acl-long)

Copied to clipboard

Challenge: Long-context understanding is crucial for large language models (LLMs) however, the ability to “output-long” is underexplored.
Approach: They propose a position ID compression approach to unlock the long-form text generation potential of large language models (LLMs).
Outcome: The proposed approach can extend LLMs' generation length by 1.5 times without compromising generation quality.
SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Long-form text generation remains a challenge for large language models . generating extended sequences often leads to degraded coherence and logical consistency .
Approach: They propose a framework that integrates explicit structured thinking into long-form text generation.
Outcome: The proposed framework surpasses even larger-scale models in evaluation and human evaluation.
RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for knowledge-intensive long texts struggle with issues like hallucinations, topic incoherence, and significant latency.
Approach: They propose a retrieval-augmented long text generation framework with writing P**lanning and I**nformation to address these challenges.
Outcome: The proposed framework outperforms state-of-the-art methods on a freshWiki-2024 dataset.
Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are prone to hallucinations and producing factually incorrect information.
Approach: They propose a framework that allows LLMs to generate citations that provide evidence for any statement.
Outcome: The proposed framework outperforms baseline approaches on three datasets and significantly outperformed baseline approaches.
Training LLMs for Optimization Modeling via Iterative Data Synthesis and Structured Validation (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a promising tool for OR, but they face challenges when dealing with complex problems.
Approach: They propose a framework that augments existing datasets and generates high-quality fine-tuning data tailored to OR.
Outcome: The proposed framework augments existing datasets and generates high-quality fine-tuning data . it prevents error propagation and ensures the quality of the generated dataset .
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks for long-form generation assess real-world queries with hard-to-verify metrics or use synthetic setups that overlook real-life intricacies.
Approach: They propose a new approach that balances verifiable and real-world assessment with Target-Anchored Evaluation.
Outcome: The proposed model balances real-world and verifiable assessment with Target-Anchored Evaluation (TAE) it generates queries, textual materials, and anchors based on verifier targets within real-life scenarios .
Progressive Generation of Long Text with Pretrained Language Models (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for "long" text generation are limited to outputs of 50-200 tokens . however, our proposed ProGen generates coherent long passages of text in a progressive manner .
Approach: They propose a method for generating coherent long passages of text in a progressive manner . they first produce domain-specific content keywords and then refine them into complete passages . human evaluation validates that their proposed generation is more coherent .
Outcome: The proposed method produces domain-specific content keywords and refines them into complete passages in multiple stages.
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines (2025.findings-acl)

Copied to clipboard

Challenge: In-context learning is an important but not fully understood ability of pre-trained large language models.
Approach: They propose a tool that generates two streams of guidelines capturing task language and format distributions and prompts them to define them by prompting.
Outcome: The proposed model improves both strong open- and closed-source LLMs by over 5% in both zero- and few-shot settings.
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models have shown a powerful ability for text generation, but undesired behaviors such as toxicity and hallucinations can manifest.
Approach: They propose to formalize text generation as a future-constrained generation problem to minimize undesirable behaviors and enforce faithfulness to instructions.
Outcome: The proposed approach is effective across three tasks, including keyword-constrained generation, toxicity reduction, and factual correctness in question-answering.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations