Search Results for author:
Found 16 papers, 2 papers with code
Training LLMs to Better Self-Debug and Explain Code
We thus propose an automated pipeline to collect a high-quality dataset for code explanation and refinement by generating a number of explanations and refinement trajectories and filtering via execution verification.
Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation
Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions based on the corpus of documents associated with the task.
Collage: Light-Weight Low-Precision Strategy for LLM Training
Large models training is plagued by the intense compute cost and limited hardware memory.
BASS: Batched Attention-optimized Speculative Sampling
Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models.
Fewer Truncations Improve Language Modeling
In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens.
CodeFort: Robust Training for Code Generation Models
Code generation models are not robust to small perturbations, which often lead to inconsistent and incorrect generations and significantly degrade the performance of these models.
Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations.
Pre-trained Recommender Systems: A Causal Debiasing Perspective
In particular, we propose to develop a generic recommender that captures universal interaction patterns by training on generic user-item interaction data extracted from different domains, which can then be fast adapted to improve few-shot learning performance in unseen new domains (with limited data).
Lightweight reranking for language model generations
We show strong improvements for selecting the best k generations for code generation tasks as well as robust improvements for the best generation for the tasks of autoformalization, summarization, and translation.
Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances
Our algorithms rely on non-uniform budget allocations among the arms where the arms with higher reward variances are pulled more often than those with lower variances.
Personalized Federated Domain Adaptation for Item-to-Item Recommendation
To mitigate this data bottleneck, we postulate that recommendation patterns learned from existing mature market segments (with private data) could be adapted to build effective warm-start models for emerging ones.
Robust Projection based Anomaly Extraction (RPE) in Univariate Time-Series
This paper presents a novel, closed-form, and data/computation efficient online anomaly detection algorithm for time-series data.
Learning Personalized Item-to-Item Recommendation Metric via Implicit Feedback
We develop and investigate a personalizable deep metric model that captures both the internal contents of items and how they were interacted with by users.
Bridging Recommendation and Marketing via Recurrent Intensity Modeling
RIM allows us to rethink recommendation in a Matching (Mtch) scenario, where the benefits of the users (e. g., ItemRec relevance) and item providers (e. g., item-exposure guarantees) are considered at the same time.
Language Models as Recommender Systems: Evaluations and Limitations
Pre-trained language models (PLMs) such as BERT and GPT learn general text representations and encode extensive world knowledge; thus, they can be efficiently and accurately adapted to various downstream tasks.
Zero-Shot Recommender Systems
This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS.
