Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
hub
Revolutionizing finance with llms: An overview of applications and insights
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
LLMs show low sycophancy to rebuttals but high sycophancy to conflicting user preferences in financial agentic tasks, with recovery methods benchmarked.
QRAFTI is a multi-agent framework using tool-calling and reflection-based planning to emulate quant research tasks like factor replication and signal testing on financial data.
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
Generates 550 roles and 33,000 questions to evaluate 10 LLMs in role-playing, finding 107,580 biased responses.
SinkProbe detects hallucinations from the concentration of attention onto a few sink tokens, and shows prior attention-based detectors implicitly use the same signal.
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.
This survey paper identifies opportunities for LLMs in low-resource language humanities research along with challenges in data accessibility, model adaptability, and cultural sensitivity.
citing papers explorer
-
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
-
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
LLMs show low sycophancy to rebuttals but high sycophancy to conflicting user preferences in financial agentic tasks, with recovery methods benchmarked.
-
QRAFTI: An Agentic Framework for Empirical Research in Quantitative Finance
QRAFTI is a multi-agent framework using tool-calling and reflection-based planning to emulate quant research tasks like factor replication and signal testing on financial data.
-
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
-
SoK: Security of Autonomous LLM Agents in Agentic Commerce
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
-
Fairness Testing of Large Language Models in Role-Playing
Generates 550 roles and 33,000 questions to evaluate 10 LLMs in role-playing, finding 107,580 biased responses.
-
Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models
SinkProbe detects hallucinations from the concentration of attention onto a few sink tokens, and shows prior attention-based detectors implicitly use the same signal.
-
A Survey on LLM-as-a-Judge
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
-
Bridging Language Models and Financial Analysis
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.
-
Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research
This survey paper identifies opportunities for LLMs in low-resource language humanities research along with challenges in data accessibility, model adaptability, and cultural sensitivity.