32 citations · 44 across the 13 of their papers we have counts for
13 papers
Active Learners as Efficient PRP Rerankers
Jeremías Figueiredo Paschmann, Juan Kaplan, Francisco Nattero +3
Pairwise Ranking Prompting (PRP) elicits pairwise preference judgments from an LLM, which are then aggregated into a ranking, usually via classical sorting algorithms. However, jud…
Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
Joaquín Polonuer, Lucas Vittor, Iñaki Arango +4
Retrieving evidence for language model queries from knowledge graphs requires balancing broad search across the graph with multi-hop traversal to follow relational links. Similarit…
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Gonzalo Ariel Meyoyan, Luciano Del Corro
Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operational complexity. We instead reu…
Entropy Sentinel: Probing Entropy Traces for LLM Monitoring
Pedro Memoli Buffa, Luciano Del Corro
Deploying LLMs raises two coupled challenges: (1) monitoring---estimating where a model underperforms as traffic drifts---and (2) prioritization---deciding where to intervene to cl…
Are Optimal Algorithms Still Optimal? Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching
Juan Wisznia, Cecilia Bolaños, Juan Tollo +4
We introduce a novel framework for analyzing sorting algorithms in pairwise ranking prompting (PRP), re-centering the cost model around LLM inferences rather than traditional pairw…
The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas
Giovanni Franco Gabriel Marraffini, Andrés Cotton, Noe Fabian Hsueh +3
The question of how to make decisions that maximise the well-being of all persons is very relevant to design language models that are beneficial to humanity and free from harm. We…
AgentInstruct: Toward Generative Teaching with Agentic Flows
Arindam Mitra, Luciano Del Corro, Guoqing Zheng +11
Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also…
sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting
Sanchit Ahuja, Kumar Tanmay, Hardik Hansrajbhai Chauhan +9
Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel app…
Orca 2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan +12
Orca 1 learns from rich signals, such as explanation traces, allowing it to outperform conventional instruction-tuned models on benchmarks like BigBench Hard and AGIEval. In Orca 2…
Automatic Pair Construction for Contrastive Post-training
Canwen Xu, Corby Rosset, Ethan C. Chau +6
Alignment serves as an important step to steer large language models (LLMs) towards human preferences. In this paper, we propose an automatic way to construct contrastive data for…
SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
Luciano Del Corro, Allie Del Giorno, Sahaj Agarwal +3
Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency result…
From Stock Prediction to Financial Relevance: Repurposing Attention Weights to Assess News Relevance Without Manual Annotations
Luciano Del Corro, Johannes Hoffart
We present a method to automatically identify financially relevant news using stock price movements and news headlines as input. The method repurposes the attention weights of a ne…
KnowNER: Incremental Multilingual Knowledge in Named Entity Recognition
Dominic Seyler, Tatiana Dembelova, Luciano Del Corro +2
KnowNER is a multilingual Named Entity Recognition (NER) system that leverages different degrees of external knowledge. A novel modular framework divides the knowledge into four ca…