Papers by Elia Bruni
Ask No More: Deciding when to guess in referential visual dialogue (C18-1)
Copied to clipboard
| Challenge: | Using a task-oriented visual dialogue model, we add a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. |
| Approach: | They augment a task-oriented visual dialogue model with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. |
| Outcome: | The proposed model can be enhanced with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. |
Agents generalize to novel levels of abstraction by using adaptive linguistic strategies (2025.findings-acl)
Copied to clipboard
| Challenge: | Abstract: Abstracts are fundamental to building well-generalizing models. |
| Approach: | They propose to use a concept-level reference game to generalize concepts . they find that agents can learn robust concepts based on which they can generalize . |
| Outcome: | The proposed model can generalize from generic to very specific concepts, while reusing many messages from training. |
Learning to request guidance in emergent language (D19-64)
Copied to clipboard
Benjamin Kolb, Leon Lang, Henning Bartsch, Arwin Gansekoele, Raymond Koopmanschap, Leonardo Romor, David Speck, Mathijs Mul, Elia Bruni
| Challenge: | Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. |
| Approach: | They extend one-directional communication by a one-bit communication channel from the learner back to the guide and limit the guidance by penalizing the learners for these requests. |
| Outcome: | The proposed guide can speed up the learning process of an imitation learning agent by providing the learner with discrete messages in an emerged language about how to solve the task. |
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat (N19-1)
Copied to clipboard
Ravi Shekhar, Aashish Venkatesh, Tim Baumgärtner, Elia Bruni, Barbara Plank, Raffaella Bernardi, Raquel Fernández
| Challenge: | Existing systems that address the abilities that need to be put to work during conversations are lacking in terms of visual grounding. |
| Approach: | They propose a visually-grounded dialogue state encoder which integrates visual grounding with dialogue system components. |
| Outcome: | The proposed system improves the GuessWhat?! game by combining guessing and asking questions with multi-task learning. |
Location Attention for Extrapolation to Longer Sequences (2020.acl-main)
Copied to clipboard
| Challenge: | Neural networks are surprisingly good at interpolating, but they are often unable to extrapolate patterns beyond the seen data. |
| Approach: | They propose to use a special type of extrapolation for natural language processing to generalize to sequences that are longer than the training ones. |
| Outcome: | The proposed model is more likely to extrapolate than models with common attention mechanisms. |
Internal and external pressures on language emergence: least effort, object constancy and frequency (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that the emergent languages rarely display salient features inherent to natural languages, such as compositionality of meaning and generalisation to novel objects. |
| Approach: | They propose to formalise the principle of least effort through an auxiliary objective and explore several game variants inspired by the principle 'object constancy' they find that the proposed sources of pressure result in emerging languages with less redundancy, more focus on high-level conceptual information, and better abilities of generalisation. |
| Outcome: | The proposed sources of pressure result in emerging languages with less redundancy, more focus on high-level conceptual information, and better abilities of generalisation. |
Context Shapes Emergent Communication about Concepts at Different Levels of Abstraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Concept-level reference game allows speakers to communicate concepts at different levels of abstraction and in different contexts. |
| Approach: | They use a symbolic dataset that disentangles concept type and context to study the influence of these factors on the emerging language. |
| Outcome: | The proposed model disentangles concept type and context to study the communication of concepts at different levels of abstraction and in different contexts. |
Emergence of Hierarchical Reference Systems in Multi-agent Communication (2022.coling-1)
Copied to clipboard
| Challenge: | a hierarchical reference system allows the selection of the most appropriate level of specificity for a given context. |
| Approach: | They propose a hierarchical reference game to study the emergence of hierarchic reference systems in artificial agents. |
| Outcome: | The proposed game shows that agents can generalize to new concepts . the hierarchical reference game is based on a simplified world . |
Can you SPLICE it together? A Human Curated Benchmark for Probing Visual Reasoning in VLMs (2025.findings-emnlp)
Copied to clipboard
Mohamad Ballout, Okajevo Wilfred, Seyedalireza Yaghoubi, Nohayr Muhammad Abdelmoneim, Julius Mayer, Elia Bruni
| Challenge: | SPLICE is a benchmark designed to probe event-based reasoning across multiple dimensions. |
| Approach: | They introduce a human-curated benchmark to probe event-based reasoning across multiple dimensions. |
| Outcome: | The proposed benchmark includes 3,381 human-filtered videos spanning 12 categories and 180 sub-categories . results show that state-of-the-art vision-language models struggle to match human performance . |
The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue (P19-1)
Copied to clipboard
| Challenge: | Using the PhotoBook dataset, we investigate shared dialogue history accumulating during conversation . human interlocutors are known to collaboratively establish a shared repository of mutual information during a conversation - this common ground is then used to optimise understanding and communication efficiency. |
| Approach: | They propose a data-collection task formulated as a collaborative game prompting two online participants to refer to images utilising both their visual context and previously established referring expressions. |
| Outcome: | The proposed model takes into account shared information accumulated in a reference chain and is important to resolve later descriptions. |
Language Modelling as a Multi-Task Problem (2021.eacl-main)
Copied to clipboard
| Challenge: | Using multitask learning, humans are optimising their behaviour towards a multitude of objectives to reach their goals in dayto-day life. |
| Approach: | They propose to study language modelling as a multi-task problem by examining the generalisation behaviour of language models as they learn the linguistic concept of Negative Polarity Items. |
| Outcome: | The proposed model is able to learn the linguistic concept of Negative Polarity Items (NPIs) and is a multi-task learning model. |
Interpretability of Language Models via Task Spaces (2024.acl-long)
Copied to clipboard
| Challenge: | linguistic interpretability is a method used to assess language models' ability to interpret outputs. |
| Approach: | They propose a method to assess LMs' language conceptualisations by 'similarity probing' and a technique to fine tune them via gradient differentials to disentangle the learning signals of linguistic phenomena. |
| Outcome: | The proposed method generalises larger models to overarching general concepts for linguistic tasks, and the generalisation patterns are stable throughout training and not marked by incisive stages. |
Co-evolution of language and agents in referential games (2021.eacl-main)
Copied to clipboard
| Challenge: | Referential games allow neural agents to learn language, but they do not take into account the learning biases of the learners. |
| Approach: | They propose to model cultural and architectural evolution in a population of agents to take into account learning biases of the language learners and let them co-evolve. |
| Outcome: | The proposed model outperforms cultural transmission in a population of agents and takes into account learning biases of the learners. |
The Grammar of Emergent Languages (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on emergent languages focus on semantics, but lack tools to analyse their properties. |
| Approach: | They propose to use unsupervised grammar induction techniques to analyse emergent languages and to examine their syntactic properties. |
| Outcome: | The proposed techniques are appropriate to analyse emergent languages and show that they exhibit syntactic properties similar to those observed in human language. |
The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study (2022.acl-long)
Copied to clipboard
| Challenge: | Obtaining human-like performance in NLP is often argued to require compositional generalisation. |
| Approach: | They re-instantiate three compositionality tests from the literature and reformulate them for neural machine translation. |
| Outcome: | The proposed models are more compositional than models trained on more data, the authors show . they also show that some non-compositional behaviours are mistakes, whereas others reflect natural variation in data. |
iVISPAR — An Interactive Visual-Spatial Reasoning Benchmark for VLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) struggle with spatial reasoning and visual alignment, despite their performance on 2D tasks. |
| Approach: | They propose a multimodal benchmark to evaluate VLMs' spatial reasoning capabilities based on the sliding tile puzzle . |
| Outcome: | The proposed model performs better on 2D tasks compared to 3D or text-based settings, but struggles with complex spatial configurations and consistently falls short of human performance. |