Papers with probability estimates
Do Neural Language Models Inferentially Compose Concepts the Way Humans Can? (2024.lrec-main)
Copied to clipboard
| Challenge: | a new study shows that language models and humans may rely on different approaches to represent and compose lexical items across sentence structure. |
| Approach: | They propose to use a dataset to test the performance of neural language models and humans on inferentially driven conceptual compositions. |
| Outcome: | The proposed model elicits probability estimates for a noun in a minimally composed phrase . RoBERTa, BERT-large, and GPT-2 exhibited the closest resemblance to human responses . |
Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia. (2023.emnlp-main)
Copied to clipboard
| Challenge: | Dementia is associated with language disorders which impede communication. |
| Approach: | They propose to use a pre-trained language model to automatically learn linguistic disorder patterns by forcing it to focus on reformulated natural language processing (NLP) tasks and associated linguistic patterns. |
| Outcome: | The proposed communication marker outperforms existing linguistic approaches and shows external validity via significant correlation with clinical markers of behaviour. |
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. |