Papers by Aldo Lipani

9 papers
Multilingual Refusal Alignment for Safer Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly used globally, but their safety and alignment can vary unpredictably between languages.
Approach: They propose a multilingual refusal alignment dataset to investigate whether alignment transfers cross-lingually and how language consistency is preserved during training.
Outcome: The proposed model can be trained on multilingual datasets without affecting general performance.
A Survey on Asking Clarification Questions Datasets in Conversational Systems (2023.acl-long)

Copied to clipboard

Challenge: Existing studies on Asking Clarification Questions (ACQs) are incomparable due to inconsistent data, experimental setups and evaluation strategies.
Approach: They analyse the current research status on Asking Clarification Questions (ACQs) and propose a set of evaluation metrics and benchmarks for multiple ACQs-related tasks.
Outcome: The proposed techniques are compared with the available datasets and evaluated against benchmarks.
Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking (2022.acl-long)

Copied to clipboard

Challenge: Existing approaches to model the relations between domains and slots fail to address these issues and can be generalized to unseen domains.
Approach: They propose a Dynamic Schema Graph Fusion Network which generates a dynamic schema graph to explicitly fuse prior slot-domain membership relations and dialogue-aware dynamic slot relations.
Outcome: The proposed model outperforms existing methods on benchmark datasets showing that it can extract users' goals or intentions as dialogue states and keep them updated over the whole dialogue.
Mitigating Context Interference for Reliable and Efficient Search Agents (2026.acl-long)

Copied to clipboard

Challenge: Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved.
Approach: They propose a distill-based context refiner to dynamically mitigate context interference . they also propose RLs that refine contexts to generate outputs .
Outcome: The proposed refiner can mitigate context interference in multi-turn search agents.
Learning to Execute Actions or Ask Clarification Questions (2022.findings-naacl)

Copied to clipboard

Challenge: Existing work on Minecraft Corpus Dataset only learns to execute instructions neglecting the importance of asking for clarifications.
Approach: They propose to annotate all builder utterances into eight types, including clarification questions, and propose a builder agent model capable of determining when to ask or execute instructions.
Outcome: The proposed model outperforms existing models on the collaborative building task with a substantial improvement.
Interpretability-based Tailored Knowledge Editing in Transformers (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for modifying in-context learning fail to analyze the instability of in-constitu learning outcomes.
Approach: They propose a model-based knowledge editing method that considers the unique information flow of each sample and aims to correct errors without costly retraining.
Outcome: The proposed method exploits the critical role of feed-forward MLPs in decoder-only models and reveals diverse attribute recall across transformer layers, guiding edits to specific features at different depths and mitigating over-editing issues.
Lexical Entrainment for Conversational Systems (2023.findings-emnlp)

Copied to clipboard

Challenge: Conversational agents are expected to possess human-like features such as lexical entrainment (LE).
Approach: They propose a dataset and a measure for LE for conversational systems to explicitly integrate LE into conversational system.
Outcome: The proposed dataset and a measure for LE for conversational systems address this human-like phenomenon.
Subsequence Based Deep Active Learning for Named Entity Recognition (2021.acl-long)

Copied to clipboard

Challenge: Active Learning (AL) has been successfully applied to Deep Learning to drastically reduce the amount of data required to achieve high performance.
Approach: They propose to query subsequences within sentences and propagate their labels to other sentences.
Outcome: The proposed approach achieves high performance on OntoNotes 5.0 and CoNLL 2003 with only 13% of training data and 27% of the training data.
Transparent and Scrutable Recommendations Using Natural Language User Profiles (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) rely on implicit or explicit feedback from users to suggest new items, resulting in a lack of transparency and a user's ability to scrutinize and modify their preferences.
Approach: They propose to use a natural language (NL) user profile to summarize a user's preferences and then use it to fine-tune a LLM using only NL profiles to make transparent and scrutable recommendations.
Outcome: The proposed model performs on two benchmarking rating prediction datasets and is comparable to existing models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations