Papers with MFS
Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding (2026.eacl-long)
Copied to clipboard
| Challenge: | Standard autoregressive decoding in large language models is short-sighted, often failing to find globally optimal reasoning paths due to token-by-token generation process. |
| Approach: | They propose a principled framework that reformulates LLM decoding as a problem of identifying an optimal stochastic process. |
| Outcome: | The proposed framework surpasses state-of-the-art methods in accuracy while significantly improving computational efficiency. |
CluBERT: A Cluster-Based Approach for Learning Sense Distributions in Multiple Languages (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to induce word senses from raw sentences lack reliable and high-coverage distributions. |
| Approach: | They propose an automatic and multilingual approach to inducing word senses from a corpus of raw sentences using an annotated corpus. |
| Outcome: | The proposed method outperforms all other methods on English and other languages. |
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions (2022.acl-long)
Copied to clipboard
| Challenge: | Existing language models can't predict the probability distribution over next words or masked words because of a single hidden state. |
| Approach: | They propose a multi-facet softmax to address the limitations of softmax . they propose LMs that can predict the next word distribution better as their sizes grow . |
| Outcome: | The proposed model achieves two-fold improvements in the perplexity of GPT-2 and BERT. |
Zero-shot Word Sense Disambiguation using Sense Definition Embeddings (P19-1)
Copied to clipboard
| Challenge: | Word Sense Disambiguation (WSD) is an open problem in Natural Language Processing . current methods treat senses as discrete labels and predict the most-frequent-Sense for unseen senses . |
| Approach: | They propose a supervised model to perform Word Sense Disambiguation (WSD) by predicting over a continuous sense embedding space rather than a discrete label space. |
| Outcome: | The proposed model generalizes over seen and unseen senses, achieving zero-shot learning. |