Gustavo Penha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Gustavo Penha has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Hugues Bouchard
Spotify, Barcelona, Spain
4 shared publications - Ali Vardasbi
Spotify, Amsterdam, Netherlands
3 shared publications - Claudia Hauff
Spotify, Delft, Netherlands
3 shared publications - Enrico Palumbo
Spotify, Turin, Italy
3 shared publications - Mounia Lalmas
Spotify, London, United Kingdom
3 shared publications - Alice Wang
Spotify, New York, NY, USA
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1885-1887
Unified Search and Recommendation Workshop
Search (IR) & recommendation (RecSys) have long been developed in parallel, despite serving the same discovery goal over shared item universes. The rise of LLMs and agentic systems is collapsing this divide, with unified architectures and generative retrieval increasingly powering both query-driven and feed-driven experiences. This workshop brings together researchers and practitioners to accelerate that unification through the first Unified Search and Recommendation Workshop (URSW), held in conjunction with the 20th ACM Conference on Recommender Systems (RecSys 2026) in Minneapolis, Minnesota, USA, in September–October 2026. We aim to define shared tasks & datasets, compare modeling approaches, and align evaluation across intent coverage, generalization, latency/cost, safety, and explainability. Expected outcomes include unification frameworks, benchmarks, reusable resources, and open challenges, aiming to establish unified search-and-recommendation research & practice.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1885-1887
Open AccessUnified Search and Recommendation Workshop
Search (IR) & recommendation (RecSys) have long been developed in parallel, despite serving the same discovery goal over shared item universes. The rise of LLMs and agentic systems is collapsing this divide, with unified architectures and generative retrieval increasingly powering both query-driven and feed-driven experiences. This workshop brings together researchers and practitioners to accelerate that unification through the first Unified Search and Recommendation Workshop (URSW), held in conjunction with the 20th ACM Conference on Recommender Systems (RecSys 2026) in Minneapolis, Minnesota, USA, in September–October 2026. We aim to define shared tasks & datasets, compare modeling approaches, and align evaluation across intent coverage, generalization, latency/cost, safety, and explainability. Expected outcomes include unification frameworks, benchmarks, reusable resources, and open challenges, aiming to establish unified search-and-recommendation research & practice.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7141-7150
From Habits to Discovery: Deploying LLMs for Personalized Generative Recommendations at Spotify
Podcast listening is often grounded in a set of favorite shows, while listener intent can evolve over time. This combination of stable preferences and changing intent motivates recommendation approaches that support both familiarity and exploration. Traditional recommender systems typically emphasize long-term interaction patterns, and are less explicitly designed to incorporate rich contextual signals or flexible, intent-aware discovery objectives. In this setting, models that can jointly reason over semantics, context, and user state offer a promising direction. Large Language Models (LLMs) provide strong semantic reasoning and contextual conditioning for discovery-oriented recommendation, but deploying them in production introduces challenges in catalog grounding, user-level personalization, and latency-critical serving. We address these challenges with GLIDE, a production-scale generative recommender for podcast discovery at Spotify. GLIDE formulates recommendation as an instruction-following task over a discretized catalog using Semantic IDs, enabling grounded generation over a large inventory. The model conditions on recent listening history and lightweight user context, while injecting long-term user embeddings as soft prompts to capture stable preferences under strict inference constraints. We evaluate GLIDE using offline retrieval metrics, human judgments, and LLM-based evaluation, and validate its impact through large-scale online A/B testing. Across experiments involving millions of users, GLIDE increases non-habitual podcast streaming on Spotify home surface by up to 5.4% and new-show discovery by up to 14.3%, while meeting production cost and latency constraints.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7141-7150
Open AccessFrom Habits to Discovery: Deploying LLMs for Personalized Generative Recommendations at Spotify
Podcast listening is often grounded in a set of favorite shows, while listener intent can evolve over time. This combination of stable preferences and changing intent motivates recommendation approaches that support both familiarity and exploration. Traditional recommender systems typically emphasize long-term interaction patterns, and are less explicitly designed to incorporate rich contextual signals or flexible, intent-aware discovery objectives. In this setting, models that can jointly reason over semantics, context, and user state offer a promising direction. Large Language Models (LLMs) provide strong semantic reasoning and contextual conditioning for discovery-oriented recommendation, but deploying them in production introduces challenges in catalog grounding, user-level personalization, and latency-critical serving. We address these challenges with GLIDE, a production-scale generative recommender for podcast discovery at Spotify. GLIDE formulates recommendation as an instruction-following task over a discretized catalog using Semantic IDs, enabling grounded generation over a large inventory. The model conditions on recent listening history and lightweight user context, while injecting long-term user embeddings as soft prompts to capture stable preferences under strict inference constraints. We evaluate GLIDE using offline retrieval metrics, human judgments, and LLM-based evaluation, and validate its impact through large-scale online A/B testing. Across experiments involving millions of users, GLIDE increases non-habitual podcast streaming on Spotify home surface by up to 5.4% and new-show discovery by up to 14.3%, while meeting production cost and latency constraints.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4938-4943
As It Was: Aligning LLM Search Evaluation with Historical User Preferences
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4938-4943
Open AccessAs It Was: Aligning LLM Search Evaluation with Historical User Preferences
- 2 January 2026
- Published by Springer Nature
- p. 3-15
Adaptive Repetition for Mitigating Position Bias in LLM-Based Ranking
- 2 January 2026
- Published by Springer Nature
- p. 3-15
Adaptive Repetition for Mitigating Position Bias in LLM-Based Ranking
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4487-4495
PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters
Listeners of long-form talk-audio content, such as podcast episodes, often find it challenging to understand the overall structure and locate relevant sections. A practical solution is to divide episodes into chapters'semantically coherent segments labeled with titles and timestamps. Since most episodes on our platform at Spotify currently lack creator-provided chapters, automating the creation of chapters is essential. Scaling the chapterization of podcast episodes presents unique challenges. First, episodes tend to be less structured than written texts, featuring spontaneous discussions with nuanced transitions. Second, the transcripts are usually lengthy, averaging about 16,000 tokens, which necessitates efficient processing that can preserve context. To address these challenges, we introduce PODTILE, a fine-tuned encoder-decoder transformer to segment conversational data. The model simultaneously generates chapter transitions and titles for the input transcript. To preserve context, each input text is augmented with global context, including the episode's title, description, and previous chapter titles. In our intrinsic evaluation, PODTILE achieved a 11% improvement in ROUGE score over the strongest previous baseline. Additionally, we provide insights into the practical benefits of auto-generated chapters for listeners navigating episode content. Our findings indicate that auto-generated chapters serve as a useful tool for engaging with less popular podcasts. Finally, we present empirical evidence that using chapter titles can enhance the effectiveness of sparse retrieval in search tasks.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4487-4495
Open AccessPODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters
Listeners of long-form talk-audio content, such as podcast episodes, often find it challenging to understand the overall structure and locate relevant sections. A practical solution is to divide episodes into chapters'semantically coherent segments labeled with titles and timestamps. Since most episodes on our platform at Spotify currently lack creator-provided chapters, automating the creation of chapters is essential. Scaling the chapterization of podcast episodes presents unique challenges. First, episodes tend to be less structured than written texts, featuring spontaneous discussions with nuanced transitions. Second, the transcripts are usually lengthy, averaging about 16,000 tokens, which necessitates efficient processing that can preserve context. To address these challenges, we introduce PODTILE, a fine-tuned encoder-decoder transformer to segment conversational data. The model simultaneously generates chapter transitions and titles for the input transcript. To preserve context, each input text is augmented with global context, including the episode's title, description, and previous chapter titles. In our intrinsic evaluation, PODTILE achieved a 11% improvement in ROUGE score over the strongest previous baseline. Additionally, we provide insights into the practical benefits of auto-generated chapters for listeners navigating episode content. Our findings indicate that auto-generated chapters serve as a useful tool for engaging with less popular podcasts. Finally, we present empirical evidence that using chapter titles can enhance the effectiveness of sparse retrieval in search tasks.
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 340-349
Bridging Search and Recommendation in Generative Retrieval: Does One Task Help the Other?
Generative retrieval for search and recommendation is a promising paradigm for retrieving items, offering an alternative to traditional methods that depend on external indexes and nearest-neighbor searches. Instead, generative models directly associate inputs with item IDs. Given the breakthroughs of Large Language Models (LLMs), these generative systems can play a crucial role in centralizing a variety of Information Retrieval (IR) tasks in a single model that performs tasks such as query understanding, retrieval, recommendation, explanation, re-ranking, and response generation. Despite the growing interest in such a unified generative approach for IR systems, the advantages of using a single, multi-task model over multiple specialized models are not well established in the literature. This paper investigates whether and when such a unified approach can outperform task-specific models in the IR tasks of search and recommendation, broadly co-existing in multiple industrial online platforms, such as Spotify, YouTube, and Netflix. Previous work shows that (1) the latent representations of items learned by generative recommenders are biased towards popularity, and (2) content-based and collaborative-filtering-based information can improve an item’s representations. Motivated by this, our study is guided by two hypotheses: [H1] the joint training regularizes the estimation of each item’s popularity, and [H2] the joint training regularizes the item’s latent representations, where search captures content-based aspects of an item and recommendation captures collaborative-filtering aspects. Our extensive experiments with both simulated and real-world data support both [H1] and [H2] as key contributors to the effectiveness improvements observed in the unified search and recommendation generative models over the single-task approaches.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 340-349
Open AccessBridging Search and Recommendation in Generative Retrieval: Does One Task Help the Other?
Generative retrieval for search and recommendation is a promising paradigm for retrieving items, offering an alternative to traditional methods that depend on external indexes and nearest-neighbor searches. Instead, generative models directly associate inputs with item IDs. Given the breakthroughs of Large Language Models (LLMs), these generative systems can play a crucial role in centralizing a variety of Information Retrieval (IR) tasks in a single model that performs tasks such as query understanding, retrieval, recommendation, explanation, re-ranking, and response generation. Despite the growing interest in such a unified generative approach for IR systems, the advantages of using a single, multi-task model over multiple specialized models are not well established in the literature. This paper investigates whether and when such a unified approach can outperform task-specific models in the IR tasks of search and recommendation, broadly co-existing in multiple industrial online platforms, such as Spotify, YouTube, and Netflix. Previous work shows that (1) the latent representations of items learned by generative recommenders are biased towards popularity, and (2) content-based and collaborative-filtering-based information can improve an item’s representations. Motivated by this, our study is guided by two hypotheses: [H1] the joint training regularizes the estimation of each item’s popularity, and [H2] the joint training regularizes the item’s latent representations, where search captures content-based aspects of an item and recommendation captures collaborative-filtering aspects. Our extensive experiments with both simulated and real-world data support both [H1] and [H2] as key contributors to the effectiveness improvements observed in the unified search and recommendation generative models over the single-task approaches.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 3182-3192
Improving Content Retrievability in Search with Controllable Query Generation
An important goal of online platforms is to enable content discovery, i.e. allow users to find a catalog entity they were not familiar with. A pre-requisite to discover an entity, e.g. a book, with a search engine is that the entity is retrievable, i.e. there are queries for which the system will surface such entity in the top results. However, machine-learned search engines have a high retrievability bias, where the majority of the queries return the same entities. This happens partly due to the predominance of narrow intent queries, where users create queries using the title of an already known entity, e.g. in book search “harry potter”. The amount of broad queries where users want to discover new entities, e.g. in music search “chill lyrical electronica with an atmospheric feeling to it”, and have a higher tolerance to what they might find, is small in comparison. We focus here on two factors that have a negative impact on the retrievability of the entities (I) the training data used for dense retrieval models and (II) the distribution of narrow and broad intent queries issued in the system. We propose CtrlQGen, a method that generates queries for a chosen underlying intent—narrow or broad. We can use CtrlQGen to improve factor (I) by generating training data for dense retrieval models comprised of diverse synthetic queries. CtrlQGen can also be used to deal with factor (II) by suggesting queries with broader intents to users. Our results on datasets from the domains of music, podcasts, and books reveal that we can significantly decrease the retrievability bias of a dense retrieval model when using CtrlQGen. First, by using the generated queries as training data for dense models we make 9% of the entities retrievable—go from zero to non-zero retrievability. Second, by suggesting broader queries to users, we can make 12% of the entities retrievable in the best case.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 3182-3192
Open AccessImproving Content Retrievability in Search with Controllable Query Generation
An important goal of online platforms is to enable content discovery, i.e. allow users to find a catalog entity they were not familiar with. A pre-requisite to discover an entity, e.g. a book, with a search engine is that the entity is retrievable, i.e. there are queries for which the system will surface such entity in the top results. However, machine-learned search engines have a high retrievability bias, where the majority of the queries return the same entities. This happens partly due to the predominance of narrow intent queries, where users create queries using the title of an already known entity, e.g. in book search “harry potter”. The amount of broad queries where users want to discover new entities, e.g. in music search “chill lyrical electronica with an atmospheric feeling to it”, and have a higher tolerance to what they might find, is small in comparison. We focus here on two factors that have a negative impact on the retrievability of the entities (I) the training data used for dense retrieval models and (II) the distribution of narrow and broad intent queries issued in the system. We propose CtrlQGen, a method that generates queries for a chosen underlying intent—narrow or broad. We can use CtrlQGen to improve factor (I) by generating training data for dense retrieval models comprised of diverse synthetic queries. CtrlQGen can also be used to deal with factor (II) by suggesting queries with broader intents to users. Our results on datasets from the domains of music, podcasts, and books reveal that we can significantly decrease the retrievability bias of a dense retrieval model when using CtrlQGen. First, by using the generated queries as training data for dense models we make 9% of the entities retrievable—go from zero to non-zero retrievability. Second, by suggesting broader queries to users, we can make 12% of the entities retrievable in the best case.