Papers with probability estimation
Word Surprisal Correlates with Sentential Contradiction in LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing models are primarily optimized for task-specific performance, lacking well-defined objectives or linguistic grounding. |
| Approach: | They propose a token-to-word decoding algorithm that extends theoretically grounded probability estimation to open-vocabulary settings. |
| Outcome: | The proposed algorithm can localize sentence-level inconsistency at the word level, establishing a quantitative link between lexical uncertainty and sentential semantics. |
On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work has shown that the optimization of variational autoencoders suffers from the posterior collapse problem. |
| Approach: | They propose a variational autoencoder that couples a VAE model with a deterministic autoencoding model and improves the parameters via weight sharing and decoder signal matching. |
| Outcome: | The proposed model improves on benchmark datasets and improves diversity of dialogue generation. |
Revisiting Source Context in Nearest Neighbor Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing research does not explicitly consider the source context when retrieving similar examples . |
| Approach: | They propose a method to improve neural machine translation via source context enhancement by integrating a source-aware distance calibration module. |
| Outcome: | The proposed approach can be integrated with representative kNN-MT baselines and achieve significant performance improvements. |
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models (2026.acl-long)
Copied to clipboard
Leyi Pan, Shuchang Tao, Yunpeng Zhai, Zheyu Fu, Liancheng Fang, Minghua He, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen
| Challenge: | Existing RL methods suffer from reliability bottlenecks due to reward sparsity and intractable computations . d-TreeRPO provides fine-grained and verifiable step-wise reward signals . |
| Approach: | They propose a reliable reinforcement learning framework for diffusion large language models that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards. |
| Outcome: | The proposed framework outperforms baseline models and achieves significant improvements across reasoning benchmarks. |