A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
hub
2307.13528 , archivePrefix=
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Presents Entity-Rubrics and AbstractEdit benchmark to measure image editing models on abstract intent, finding standard models struggle to balance edit intent with image preservation.
A systematic analysis of 284 manually reviewed papers plus 1.8k+ others from 2023-2025 reveals under-reporting of human evaluation study design details, creating ambiguity in what was measured and how.
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
Authors build a three-stage risk taxonomy identifying 32 specific risks in AI-based automated fact-checking and show it surfaces risks missed by the STRIDE method when applied to the DEFAME system.
MultiHaluDet uses multi-layer hidden-state probing, multi-scale attention, and a calibrated classifier ensemble to detect multilingual hallucinations, reporting up to 98.55% AUROC on English benchmarks and strong cross-lingual transfer to French, Bangla, and Amharic.
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
An uncertainty-gated fact-checking system decomposes claims atomically, verifies them against context, and selectively searches the web only for uncertain facts, outperforming benchmarks while abstaining on conflicts.
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
Three metrics for measuring comprehensiveness in LLM text generation are evaluated, with a simple end-to-end LLM approach showing surprising effectiveness despite lower robustness and interpretability.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
Fine-tuned compact models achieve strong multilingual performance and large efficiency gains over LLMs on production data from 114 languages for claim detection and 28 for veracity prediction.
citing papers explorer
-
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
-
Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis
Presents Entity-Rubrics and AbstractEdit benchmark to measure image editing models on abstract intent, finding standard models struggle to balance edit intent with image preservation.
-
Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation
A systematic analysis of 284 manually reviewed papers plus 1.8k+ others from 2023-2025 reveals under-reporting of human evaluation study design details, creating ambiguity in what was measured and how.
-
Design and Report Benchmarks for Knowledge Work
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
-
Principled Detection of Hallucinations in Large Language Models via Multiple Testing
The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.
-
LIMO: Less is More for Reasoning
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
-
Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation
Authors build a three-stage risk taxonomy identifying 32 specific risks in AI-based automated fact-checking and show it surfaces risks missed by the STRIDE method when applied to the DEFAME system.
-
MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing
MultiHaluDet uses multi-layer hidden-state probing, multi-scale attention, and a calibrated classifier ensemble to detect multilingual hallucinations, reporting up to 98.55% AUROC on English benchmarks and strong cross-lingual transfer to French, Bangla, and Amharic.
-
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
-
Uncertainty-Aware Web-Conditioned Scientific Fact-Checking
An uncertainty-gated fact-checking system decomposes claims atomically, verifies them against context, and selectively searches the web only for uncertain facts, outperforming benchmarks while abstaining on conflicts.
-
100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
-
Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation
Three metrics for measuring comprehensiveness in LLM text generation are evaluated, with a simple end-to-end LLM approach showing surprising effectiveness despite lower robustness and interpretability.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs
Fine-tuned compact models achieve strong multilingual performance and large efficiency gains over LLMs on production data from 114 languages for claim detection and 28 for veracity prediction.
- BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation