Papers by Brendon Boldt
XferBench: a Data-Driven Benchmark for Emergent Language (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to teach models to "language" are full of bias, toxicity, and potential intellectual property violations. |
| Approach: | They propose a benchmark for evaluating the overall quality of emergent languages using data-driven methods. |
| Outcome: | The proposed benchmark is based on utterances from the emergent language and is validated using human, synthetic, and emergentic language baselines. |
Searching for the Most Human-like Emergent Language (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on emergent communication systems to generate languages with high statistical similarity to human languages has not been done. |
| Approach: | They propose to optimize a signalling game-based emergent communication environment to generate state-of-the-art emergentic languages with a high degree of similarity to human language. |
| Outcome: | The proposed language generates state-of-the-art on XferBench benchmark, demonstrating its similarity to human language and entropy-minimization properties. |
PRiSM: Benchmarking Phone Realization in Speech Models (2026.acl-long)
Copied to clipboard
Shikhar Bharadwaj, Chin-Jou Li, Yoonjae Kim, Kwanghee Choi, Eunjung Yeo, Ryan Soh-Eun Shim, Hanyu Zhou, Brendon Boldt, Karen Rosero, Kalvin Chang, Darsh Agrawal, Keer Xu, Chao-Han Huck Yang, Jian Zhu, Shinji Watanabe, David R. Mortensen
| Challenge: | Existing evaluations of phone recognition systems only measure surface-level transcription accuracy. |
| Approach: | They propose to standardize transcription-based evaluation and assess downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. |
| Outcome: | The proposed system outperforms LALMs in clinical, educational, and multilingual settings. |
Morpheme Induction for Emergent Language (2025.emnlp-main)
Copied to clipboard
| Challenge: | CSAR is a greedy algorithm that weights morphemes based on mutual information between forms and meanings, then removes it from the corpus and repeats the process to induce more morphs. |
| Approach: | They propose an algorithm that weights morphemes based on mutual information between forms and meanings, selects highest-weighted pair, removes it from corpus, and repeats process to induce further morphs. |
| Outcome: | The proposed algorithm makes reasonable predictions in adjacent domains. |
Communicating in Emergent Language with an Induced Morphological Phrasebook (2026.acl-long)
Copied to clipboard
| Challenge: | a major challenge in studying emergent languages is interpreting how they convey meaning-neural networks may invent communication systems lacking features of human language. |
| Approach: | They build rule-based emergent language agents using form-meaning mappings induced from ELs and test their communicative performance in the EL environment. |
| Outcome: | The proposed model shows that EL agents rely on repetition and morpheme ordering to convey meaning. |
Case Study: Deontological Ethics in NLP (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work in natural language processing (NLP) has focused on ethical challenges . ethical foundations of NLP systems have not been explored . |
| Approach: | They propose to use deontological ethics to analyze ethical issues in natural language processing from the perspective of NLP. |
| Outcome: | The proposed ethical frameworks are based on the generalization principle and respect for autonomy through informed consent. |