CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization (D18-1)
Copied to clipboard
| Challenge: | Maximum-likelihood estimation (MLE) is widely used for text-generation based natural language processing applications. |
| Approach: | They propose a method to train models with maximum-likelihood estimation using a differentiable surrogate of longest common subsequence measure that captures sequence-level structure similarity. |
| Outcome: | Experimental results show that the proposed approach improves on the current MLE approach for downstream tasks like text summarization and machine translation. |
Similar Papers
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)
Copied to clipboard
Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
| Challenge: | Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards. |
| Approach: | They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates. |
| Outcome: | The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods. |
Sequence-level Large Language Model Training with Contrastive Preference Optimization (2025.findings-naacl)
Copied to clipboard
| Challenge: | a new method to improve the performance of large language models requires a small computational cost. |
| Approach: | They propose a CPO procedure that can inject sequence-level information into the model at any training stage without expensive human labeled data. |
| Outcome: | The proposed objective surpasses the next token prediction in terms of win rate in instruction-following and text generation tasks. |
GECSum: Generative Evaluation-Driven Sequence Level Contrastive Learning for Abstractive Summarization (2024.lrec-main)
Copied to clipboard
| Challenge: | Abstractive summarization is a technique in natural language processing that involves generating a summary of a source document by creating new sentences and phrases. |
| Approach: | They propose a sequence-level contrastive learning framework that leverages the semantic understanding capabilities of the abstractive model itself to evaluate summary in reference-based settings. |
| Outcome: | The proposed framework outperforms the state-of-the-art in four summarization datasets. |
LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models excel in generating coherent and contextually rich outputs, but their capacity to handle long-form contexts is limited by fixed-length position embeddings. |
| Approach: | They propose a method that enables the efficient processing long-form sequences beyond the model’s length limit through recurrent compression without retraining the entire model. |
| Outcome: | The proposed method significantly improves LLM’s ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance. |
SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)
Copied to clipboard
Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Lintao Ma, Xingyu Lu, Jun Zhou, Pengfei Liu, Jiancan Wu, Xiang Wang
| Challenge: | Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences. |
| Approach: | They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context. |
| Outcome: | The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs. |
Historical Text Normalization with Delayed Rewards (P19-1)
Copied to clipboard
| Challenge: | Recent work on a novel approach to historical text normalization has shown that policy gradient fine-tuning improves accuracy across languages. |
| Approach: | They propose to train sequence-to-sequence models with simple token-level log-likelihood with reinforcement learning to optimize for exact matches. |
| Outcome: | The proposed model outperforms phrase-based models in the evaluation metric for historical text normalization across languages. |
Incorporating Exponential Smoothing into MLP: a Simple but Effective Sequence Model (2024.findings-naacl)
Copied to clipboard
| Challenge: | Structured State Space models (SSMs) have been used for long-range sequence learning but are limited in their complexity and computational and memory requirements. |
| Approach: | They propose to incorporate a simple SSM into an element-wise MLP to reduce inductive bias. |
| Outcome: | The proposed model achieves comparable results to existing models on the LRA benchmark. |
Training Long-Context LLMs Efficiently via Chunk-wise Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in long-context large language models have demonstrated superior retrieval quality compared to retrievalaugmented generation (RAG) approaches. |
| Approach: | They propose a memory-efficient training paradigm that partitions lengthy inputs into manageable chunks. |
| Outcome: | The proposed model expands maximum sequence length from 1K to 16K tokens on a single RTX 3090 GPU, while SpaCO achieves accelerated training speed. |
HiPool: Modeling Long Documents Using Graph Neural Networks (2023.acl-short)
Copied to clipboard
| Challenge: | Recent work on pretraining languages have achieved satisfying results in many NLP tasks, but they are still restricted by a pre-defined maximum length. |
| Approach: | They propose a graph-based method to model sentence-level information using a fixed length and graphs to model intra- and cross-sentence correlations. |
| Outcome: | The proposed model outperforms baseline models by 2.6% in F1 score, and 4.8% on the longest sequence dataset. |
Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing language models generate repetitive texts with greedy decoding or beam search. |
| Approach: | They propose a self-contrastive training technique to penalize the output of a premature checkpoint of the same model when it incorrectly predicts repetition. |
| Outcome: | The proposed training mitigates repetition while maintaining fluency while minimizing the overestimation of token-level repetition probabilities. |