Related papers: Synapse: Evolving Job-Person Fit with Explainable …
Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…
Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement, for example, by reconstructing datasets with refined…
There has been limited success for dense retrieval models in multilingual retrieval, due to uneven and scarce training data available across multiple languages. Synthetic training data generation is promising (e.g., InPars or Promptagator),…
Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems…
AI-assisted resume tailoring systems commonly operate on a single uploaded resume, which limits their ability to recover relevant experience omitted from the current draft and makes it difficult for users to distinguish grounded edits from…
Scientific Workflow Management Systems (SWfMSs) such as Galaxy have become essential infrastructure in bioinformatics, supporting the design, execution, and sharing of complex multi-step analyses. Despite hosting hundreds of reusable…
Motivated by the need to emulate workload execution characteristics on high-performance and distributed heterogeneous resources, we introduce Synapse. Synapse is used as a proxy application (or "representative application") for real…
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…
Candidate retrieval is a fundamental issue in recommendation system. Given user's recommendation request, relevant candidates need to be retrieved in realtime for subsequent ranking operations. Considering that the retrieval operation is…
Multi-step agentic retrieval systems based on large language models (LLMs) have demonstrated remarkable performance in complex information search tasks. However, these systems still face significant challenges in practical applications,…
The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and…
Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items…
The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and…
When developing new large language models (LLMs), a key step is evaluating their final performance, often by computing the win-rate against a reference model based on external feedback. Human feedback is the gold standard, particularly for…
With the advent of large language models (LLMs), there has been a great deal of interest in applying them to solve difficult programming tasks. Recent work has demonstrated their potential at program optimization, a key challenge in…
The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP…
Evolutionary algorithms excel in solving complex optimization problems, especially those with multiple objectives. However, their stochastic nature can sometimes hinder rapid convergence to the global optima, particularly in scenarios…
Crafting the ideal, job-specific resume is a challenging task for many job applicants, especially for early-career applicants. While it is highly recommended that applicants tailor their resume to the specific role they are applying for,…
Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval…
Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples. This makes it hard for data-driven RSs to cater to a diverse set of users due to the varying properties…