Papers by Fabio Massimo Zanzotto

13 papers
Sounding vs. Being an Expert: Disentangling Authority, Register and Cultural Impact in Sycophantic LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models exhibit sycophancy, a tendency to align with user assertions even when they conflict with factual correctness.
Approach: They propose an adversarial evaluation framework that isolates two drivers of credibility: explicit authority (credentials) and implicit authority (linguistic register).
Outcome: The proposed framework disentangles two drivers of credibility: explicit authority (credentials) and implicit authority (linguistic register).
Every time I fire a conversational designer, the performance of the dialogue system goes down (2022.lrec-1)

Copied to clipboard

Challenge: Incorporating handwritten domain scripts into neural-based task-oriented dialogue systems may be an effective way to reduce the need for large sets of annotated dialogues.
Approach: They propose a system where domain scripts are coded in semi-logical rules and evaluated semi-logic rules produced by differently-skilled conversational designers.
Outcome: The proposed system outperforms state-of-the-art systems when trained with smaller sets of annotated dialogues.
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing pruning algorithms suffer from limitations such as architecture specificity and reliance on demanding calculations.
Approach: They propose a pruning algorithm based on Kernel Density Estimation . it preserves most significant parameters while restoring others to their pre-training state .
Outcome: The proposed pruning algorithm achieves better performance than the original unpruned version.
Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) memorize and therefore, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII).
Approach: They propose a method that uses a model knowledge to memorize PII from training data to mitigate the memorization of PI I.
Outcome: The proposed method reduces the number of leaked PIIs in a number of configurations while making it more robust against privacy Training Data Extraction attacks.
Lexical Popularity: Quantifying the Impact of Pre-training for LLM Performance (2026.eacl-long)

Copied to clipboard

Challenge: Large Language Models excel in varied tasks, but their mechanisms remain unclear . current LLMs' development has put this assumption in jeopardy, authors say .
Approach: They examine whether LLMs learn generalized linguistic abstraction or rely on surface-level features that match their pre-training data.
Outcome: The proposed model can learn generalized linguistic abstraction or rely on surface-level features that match their pre-training data.
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations (2020.emnlp-main)

Copied to clipboard

Challenge: Syntactic parsers are losing their centrality in downstream tasks due to the success of large-scale textual representation learners.
Approach: They propose to embed symbolic syntactic parse trees into artificial neural networks to visualize how syntax is used in inference.
Outcome: The proposed encoder can visualize how syntax is used in inference.
Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to ground large language models (LLMs) with RAGs are limited by the heterogeneity of knowledge retrieved.
Approach: They propose a modular approach guided by Argumentative Explanations that evaluates retrieved information by comparing, contrasting and resolving conflicting perspectives.
Outcome: The proposed framework significantly improves RAG approaches, requiring low-impact computational effort and providing robustness to knowledge perturbations.
Thinking in Schemas: Robust Syllogistic Reasoning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: syllogistic reasoning models often mistake what sounds true for what is formally valid . content effect is a limitation of sluggish reasoning, which can lead to invalid conclusions . eisape et al., 2024: a key open problem for formal inference in natural language.
Approach: They propose a schema-guided framework that disentangles semantic plausibility from logical validity.
Outcome: The proposed framework outperforms existing frameworks while reducing CE.
Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL translation (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) understand textual description to generate code in zero-shot scenarios, but there is a possibility that this ability may be influenced by having seen target textual descriptions and the related code.
Approach: They propose a method to detect Data Contamination in Large Language Models (LLMs) and analyze their results on Termite and Spider Datasets to investigate their method.
Outcome: The proposed method detects data contamination in GPTs and analyzes its performance on unfamiliar datasets.
Lacking the Embedding of a Word? Look it up into a Traditional Dictionary (2022.findings-acl)

Copied to clipboard

Challenge: Word embeddings are powerful dictionaries, but they fail to give sense to rare words . a large body of research is devoted to devising ways to capture word meaning .
Approach: They propose to use definitions retrieved from traditional dictionaries to build word embeddings for rare words.
Outcome: The proposed methods outperform state-of-the-art methods for embeddings of unknown words . the proposed methods significantly outperformed the BERT method for OOV words compared to the proposed method .
A Tree-of-Thoughts to Broaden Multi-step Reasoning across Languages (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods for eliciting Large Language Models (LLMs) to solve complex tasks are limited to English due to the imbalance in the distribution of pre-training data.
Approach: They propose a method for aligning Cross-lingual CoT reasoning across languages . they propose eliciting Large Language Models to solve complex tasks step-by-step .
Outcome: The proposed method outperforms existing prompting methods by reducing interactions and achieving state-of-the-art performance.
Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Prior work has focused on activation steering for Large Language Models (LLMs) this technique can be used to improve reasoning accuracy and transferability across languages.
Approach: They propose to use activation steering to steer models towards a cross-lingual reasoning space.
Outcome: The proposed techniques generalise well to multilingual datasets while minimizing language modelling performance.
Position Paper: MeMo: Towards Language Models with Associative Memory Mechanisms (2025.findings-acl)

Copied to clipboard

Challenge: Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning.
Approach: They propose an architecture that explicitly memorizes sequences of tokens in layered associative memories.
Outcome: The proposed architecture shows that memorization is a fundamental ability of large language models, achieved through learning.

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