Papers with Phi-4
TTD-SQL: Tree-Guided Token Decoding for Efficient and Schema-Aware SQL Generation (2025.emnlp-industry)
Copied to clipboard
Chetan Sharma, Ramasuri Narayanam, Soumyabrata Pal, Kalidas Yeturu, Shiv Kumar Saini, Koyel Mukherjee
| Challenge: | Large language models (LLMs) have achieved state-of-the-art accuracy on benchmarks like Spider and BIRD, but inference latency due to sequential autoregressive decoding remains a challenge for real-time deployments. |
| Approach: | a new framework integrates SQL grammar and database schema constraints into the decoding process . tree-Guided Token Decoding (TTD-SQL) precomputes token-level decision trees over SQL keywords, table names, and column identifiers . |
| Outcome: | a new framework reduces schema hallucinations and inference latency due to autoregressive decoding . tree-Guided Token Decoding achieves 19.96% token-rate speedups . |
MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MedCOD integrates domain-specific structured knowledge into large language models . evaluators evaluated four open-source LLMs with structured prompts . |
| Approach: | They propose a framework that integrates domain-specific structured knowledge into large language models . they constructed a parallel corpus of 2,999 English-Spanish MedlinePlus articles . |
| Outcome: | The proposed framework improves translation quality across four open-source LLMs. |
MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent smaller language models rely on synthetic data generated using larger Language models. |
| Approach: | They propose a method for generating synthetic data that enhances diversity through meta-prompting . they use 25 million tokens of synthetic data generated by a language model orchestrated by multiple “expert” LLM agents to collaboratively generate data. |
| Outcome: | The proposed method outperforms the base LLM in Finance and Biomedicine with 25 million tokens of synthetic data. |
CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression (2025.findings-emnlp)
Copied to clipboard
Dayin Gou, Sanghyun Byun, Nilesh Malpeddi, Gabrielle De Micheli, Prathamesh Vaste, Jacob Song, Woo Seong Chung
| Challenge: | Large Language Models typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. |
| Approach: | They propose a corrective Adaptor with group Residual Vector Quantization that can be used to compress the embedding layer without requiring specialized hardware. |
| Outcome: | The proposed corrective adaptor can achieve lower average bitwidth-per-parameter while maintaining reasonable perplexity and accuracy compared to scalar quantization. |
Multimodal In-context Learning for ASR of Low-resource Languages (2026.findings-acl)
Copied to clipboard
| Challenge: | In-context learning with large language models addresses this limitation, but prior work focuses on high-resource languages covered during training and text-only settings. |
| Approach: | They propose to use multimodal ICL to learn unseen languages with multimodal learning to improve ASR in large language models. |
| Outcome: | The proposed model outperforms existing models on unseen languages with multimodal ICL (MICL) and cross-lingual transfer learning matches or outperformed models without using target-language data. |