Papers by Xuan-Phi Nguyen
J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly being used for reasoning intensive tasks. |
| Approach: | They propose an algorithm that trains judges to be robust to positional biases . they also propose a benchmark that evaluates judges in diverse reasoning settings . |
| Outcome: | The proposed algorithm outperforms GPT-4o and the next best small judge by 6.7% and 9% on ReasoningJudgeBench and JudgeBench. |
Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | ChatGPT and GPT-4 are popular as evaluation metric for complex generative tasks . however, they are not ready as human replacements due to significant limitations . |
| Approach: | They conduct extensive analysis to examine the stability and reliability of LLMs as automatic evaluators for abstractive summarization. |
| Outcome: | The proposed methods outperform the commonly used automatic metrics but are not ready for human evaluation due to significant limitations. |
ParaICL: Towards Parallel In-Context Learning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to improve ICL performance are limited by the length of the input context. |
| Approach: | They propose a method that utilizes all demonstration examples without exceeding the manageable context length. |
| Outcome: | The proposed method can be scaled up to integrate with existing methods. |
Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are known to perform tasks by simply observing few exemplars, but performance among under-represented languages falls behind due to pre-training data imbalance. |
| Approach: | They propose to assemble synthetic exemplars from high-resource languages to prompt LLMs to translate from any language into English and use them to create intra-lingual exemplar models to perform tasks in target languages. |
| Outcome: | The proposed method outperforms supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages. |
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. |
| Approach: | They propose an algorithm that uses early LLM layers as filters to select and compress input tokens, reducing the context length for subsequent processing. |
| Outcome: | The proposed method outperforms existing techniques on the Needle in a Haystack task while demonstrating comparable performance on the LongBench challenge. |
Differentiable Window for Dynamic Local Attention (2020.acl-main)
Copied to clipboard
| Challenge: | Existing general purpose components for learning differentiable windows are hard to optimize. |
| Approach: | They propose a new neural module and general purpose component for dynamic window selection that can enable more focused attentions over the input regions. |
| Outcome: | The proposed approach improves on a myriad of NLP tasks including machine translation, sentiment analysis, subject-verb agreement and language modeling. |
RST Parsing from Scratch (2021.naacl-main)
Copied to clipboard
| Challenge: | Fig. 1 shows a document level discourse parser that performs top-down end-to-end parsing without requiring segmentation . |
| Approach: | They propose a top-down end-to-end formulation of document level discourse parsing in the Rhetorical Structure Theory framework. |
| Outcome: | The proposed model outperforms existing methods in end-to-end parsing and parse with gold segmentation without handcrafted features. |
Demystifying Domain-adaptive Post-training for Financial LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Domain-adaptive post-training of large language models (LLMs) has emerged as promising approach for specialized domains such as medicine and finance. |
| Approach: | They propose a system to identify optimal adaptation criteria and training strategies for LLMs for the finance domain. |
| Outcome: | The proposed model achieves state-of-the-art performance across a wide range of financial tasks. |
SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)
Copied to clipboard
Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing
| Challenge: | Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages. |
| Approach: | They propose a series of language models that specifically focuses on Southeast Asian languages. |
| Outcome: | SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations . |
A Conditional Splitting Framework for Efficient Constituency Parsing (2021.acl-long)
Copied to clipboard
| Challenge: | Developing efficient and effective parsing solutions has always been a key focus in NLP. |
| Approach: | They propose a generic seq2seq parsing framework that casts constituency parsers into a series of conditional splitting decisions. |
| Outcome: | The proposed framework outperforms state-of-the-art (SoTA) methods in discourse parsing . it is based on a syntactic and discourse parsed model and is linear in number of nodes . |
Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math (2026.acl-long)
Copied to clipboard
| Challenge: | Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition . |
| Approach: | They propose a human-annotated step-level verification benchmark that measures step- level verifiers at the frontier. |
| Outcome: | The proposed benchmark outperforms closed-source models in step-level verification and the impact of scaling verifier compute. |
A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models have been used for abstractive single-document summarization (SDS) but they may not be suitable for multi-document summary (MDS) |
| Approach: | They propose to enforce hierarchy on both encoder and decoder to facilitate multi-document interactions for MDS. |
| Outcome: | Xiao et al. (2019) outperforms or is competitive with the previous best models. |
Efficient Constituency Parsing by Pointing (2020.acl-main)
Copied to clipboard
| Challenge: | Constituency parsing is a core task in natural language processing (NLP) Existing methods for constituency paring are greedy transition-based or globally optimized. |
| Approach: | They propose a constituency parsing model that casts the problem into a series of pointing tasks. |
| Outcome: | The proposed model achieves 92.78 F1 without pre-trained models, which is faster than existing models. |