Papers by Songbo Hu
Quantifying Language Disparities in Multilingual Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Contemporary NLP development relies on digital language datasets to build large language models. |
| Approach: | They propose a framework that disentangles confounding variables and introduces interpretable metrics to quantify model performance and language disparities. |
| Outcome: | The proposed framework provides a more reliable measurement of model performance and language disparities for low-resource languages. |
Multi 3 WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems (2023.tacl-1)
Copied to clipboard
Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen
| Challenge: | Task-oriented dialog (TOD) is one of the central objectives, hallmarks, and applications of machine intelligence. |
| Approach: | They propose a multilingual, multi-domain, multiparallele ToD dataset that offers culturally adapted dialogs in 4 languages for training and evaluation of multilingual and cross-lingual systems. |
| Outcome: | The proposed dataset is large-scale and culturally adapted to enable training and evaluation of multilingual and cross-lingual ToD systems. |
Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering (2026.acl-long)
Copied to clipboard
Shuliang Liu, Songbo Yang, Dong Fang, Sihang Jia, Yuqi Tang, Lingfeng Su, Ruoshui Peng, Yibo Yan, Xin Zou, Xuming Hu
| Challenge: | Existing approaches to overcome object hallucination are limited . Existing mitigations include costly retraining and a training-free inference framework . |
| Approach: | They propose a training-free inference framework that simulates a metacognitive self-correction process. |
| Outcome: | The proposed framework reduces object hallucination rates by 12.67% on MMHal-Bench and improves accuracy by 5.8% on POPE. |
DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models (2024.naacl-demo)
Copied to clipboard
| Challenge: | DIALIGHT is a toolkit for developing and evaluating multilingual Task-Oriented Dialogue systems. |
| Approach: | They propose a toolkit for developing and evaluating multilingual Task-Oriented Dialogue systems which facilitates systematic evaluations and comparisons between ToD systems using pretrained language models and those utilising the zero-shot and in-context learning capabilities of Large Language Models. |
| Outcome: | The toolkit enables systematic evaluations between ToD systems using pretrained language models and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs). |
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems (2023.emnlp-main)
Copied to clipboard
Songbo Hu, Han Zhou, Moy Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić
| Challenge: | Existing systems trained for Arabic or Turkish using annotated data fully parallel to English ToD data still exhibit diminished ToD task performance. |
| Approach: | They define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages. |
| Outcome: | The proposed measures capture disparities across languages and within individual languages. |
Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems (2024.lrec-main)
Copied to clipboard
| Challenge: | End-to-end task-oriented dialogue systems fall into the so-called ‘likelihood trap’, resulting in generated responses which are dull, repetitive, and inconsistent with dialogue history. |
| Approach: | They propose a reranking method to select high-quality items from the initial overgenerated list without the availability of the gold response. |
| Outcome: | The proposed method is based on a multi-woz dataset and human evaluation. |
Can Pretrained Language Models (Yet) Reason Deductively? (2023.eacl-main)
Copied to clipboard
| Challenge: | Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks. |
| Approach: | They conduct a comprehensive evaluation of the learnable deductive reasoning capability of pretrained language models and compare their performance against simple adversarial surface form edits. |
| Outcome: | The models are able to generalise learned logic rules and perform inconsistently against simple adversarial surface form edits, but catastrophically forget the previously learnt knowledge. |
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking (2026.findings-acl)
Copied to clipboard
Songbo Hu, Yinhong Liu, Ej Zhou, Evgeniia Razumovskaia, Xiaobin Wang, Alexander Fraser, Ivan Vulić, Anna Korhonen
| Challenge: | Creating spoken dialogue datasets is methodologically challenging due to the personally identifiable nature of speech signals. |
| Approach: | They propose a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation-based spoken dialogue systems. |
| Outcome: | The proposed dataset includes 6,000 information-seeking dialogues and 163 hours of user speech recorded from native speakers of four official WHO languages. |