arXiv subjects

Sahil Bansal

Publications and source records attributed to Sahil Bansal.

6 recordsLinked to original sources

arXiv2026

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck. As embedding-based retrieval approaches rely on compact encoders that may under-capture specialized tool semantics, parametric tool retrieval addresses this by encoding each tool as a virtual token appended to the LLM vocabulary, fine-tuned in two stages (memorization then retrieval SFT) to use the LLM as a retriever, achieving strong performance on standard ToolBench retrieval benchmarks. Yet these benchmarks use verbose, fully-specified queries, and their evaluation applies constrained decoding that restricts outputs to valid token paths, neither reveals whether the model actually understands its tools. We introduce \textbf{ToolSense}, an open-source LLM-powered diagnostic framework that takes any tool catalog as input and automatically generates three benchmarks: a Realistic Retrieval Benchmark (RRB) with queries at three ambiguity tiers, an MCQ probing benchmark, and a QA probing benchmark. Applying ToolSense to ToolBench (~47k tools) and evaluating five parametric model training configurations reveals a knowledge-retrieval dissociation: on RRB queries, several configurations collapse by ~50-64 percentage points compared to fully-specified ToolBench benchmarks, falling below the embedding-model baseline. Additionally, despite strong retrieval performance, some models score near-random on factual probes, suggesting a knowledge-retrieval dissociation. We open-source the ToolSense framework and the ToolBench diagnostic benchmarks at https://github.com/SAP/toolsense.

cs.AI↗

arXiv2025

Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planning

Effective tool pre-selection via retrieval is essential for AI agents to select from a vast array of tools when identifying and planning actions in the context of complex user queries. Despite its central role in planning, this aspect remains underexplored in the literature. Traditional approaches rely primarily on similarities between user queries and tool descriptions, which significantly limits retrieval accuracy, specifically when handling multi-step user requests. To address these limitations, we propose a Knowledge Graph (KG)-based tool retrieval framework that captures the semantic relationships between tools and their functional dependencies. Our retrieval algorithm leverages ensembles of 1-hop ego tool graphs to model direct and indirect connections between tools, enabling more comprehensive and contextual tool selection for multi-step tasks. We evaluate our approach on a synthetically generated internal dataset across six defined user classes, extending previous work on coherent dialogue synthesis and tool retrieval benchmarks. Results demonstrate that our tool graph-based method achieves 91.85% tool coverage on the micro-average CompleteRecall metric, compared to 89.26% for re-ranked semantic-lexical hybrid retrieval, the strongest non-KG baseline in our experiments. These findings support our hypothesis that the structural information modeled in the graph provides complementary signals to pure similarity matching, particularly for queries requiring sequential tool composition.

cs.AI↗

arXiv2025

Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scale

We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval-Augmented Generation (GraphRAG) in enterprise environments. While GraphRAG has shown promise for multi- hop reasoning and structured retrieval, its adoption has been limited due to reliance on expensive large language model (LLM)-based extraction and complex traversal strategies. To address these challenges, we introduce two core innovations: (1) an efficient knowledge graph construction pipeline that leverages dependency parsing to achieve 94% of LLM-based performance (61.87% vs. 65.83%) while significantly reducing costs and improving scalability; and (2) a hybrid retrieval strategy that fuses vector similarity with graph traversal using Reciprocal Rank Fusion (RRF), maintaining separate embeddings for entities, chunks, and relations to enable multi-granular matching. We evaluate our framework on two enterprise datasets focused on legacy code migration and demonstrate improvements of up to 15% and 4.35% over vanilla vector retrieval baselines using LLM-as-Judge evaluation metrics. These results validate the feasibility of deploying GraphRAG in production enterprise environments, demonstrating that careful engineering of classical NLP techniques can match modern LLM-based approaches while enabling practical, cost-effective, and domain-adaptable retrieval-augmented reasoning at scale.

cs.AI↗

arXiv2025

Domain specific ontologies from Linked Open Data (LOD)

Logical and probabilistic reasoning tasks that require a deeper knowledge of semantics are increasingly relying on general purpose ontologies such as Wikidata and DBpedia. However, tasks such as entity disambiguation and linking may benefit from domain specific knowledge graphs, which make it more efficient to consume the knowledge and easier to extend with proprietary content. We discuss our experience bootstrapping one such ontology for IT with a domain-agnostic pipeline, and extending it using domain-specific glossaries.

cs.IR↗

arXiv2024

Argument-Aware Approach To Event Linking

Event linking connects event mentions in text with relevant nodes in a knowledge base (KB). Prior research in event linking has mainly borrowed methods from entity linking, overlooking the distinct features of events. Compared to the extensively explored entity linking task, events have more complex structures and can be more effectively distinguished by examining their associated arguments. Moreover, the information-rich nature of events leads to the scarcity of event KBs. This emphasizes the need for event linking models to identify and classify event mentions not in the KB as ``out-of-KB,'' an area that has received limited attention. In this work, we tackle these challenges by introducing an argument-aware approach. First, we improve event linking models by augmenting input text with tagged event argument information, facilitating the recognition of key information about event mentions. Subsequently, to help the model handle ``out-of-KB'' scenarios, we synthesize out-of-KB training examples from in-KB instances through controlled manipulation of event arguments. Our experiment across two test datasets showed significant enhancements in both in-KB and out-of-KB scenarios, with a notable 22% improvement in out-of-KB evaluations.

cs.CL↗

arXiv2020

Using Image Captions and Multitask Learning for Recommending Query Reformulations

Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results. We aim to enhance the query recommendation experience for a commercial image search engine. Our proposed methodology incorporates current state-of-the-art practices from relevant literature -- the use of generation-based sequence-to-sequence models that capture session context, and a multitask architecture that simultaneously optimizes the ranking of results. We extend this setup by driving the learning of such a model with captions of clicked images as the target, instead of using the subsequent query within the session. Since these captions tend to be linguistically richer, the reformulation mechanism can be seen as assistance to construct more descriptive queries. In addition, via the use of a pairwise loss for the secondary ranking task, we show that the generated reformulations are more diverse.

cs.IR↗