AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
Rickard Stureborg, Dimitris Alikaniotis, and Yoshi Suhara
10 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
10
Pith papers citing it
2
external citations · external index
representative citing papers
No detectable self-preference in LLMs accepting verified fixes to their own IFEval drafts versus neutral judges across four models and 85 comparisons (gap -5.1 pp, CI crossing zero).
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
Iterative self-finetuning of LLMs mostly fails to amplify seeded behavioral traits, with amplification limited to specific DPO setups and often harming coherence.
A score-ranking loss enables controllable summarization by aligning outputs to evaluation scores, matching SOTA performance with dimension-specific control on LLaMA, Qwen, and Mistral.
Self-preference bias persists in rubric-based LLM evaluation even with fully objective, programmatically verifiable rubrics, and can shift subjective medical-chat scores by up to ~10 points.
LLMs judge their own outputs higher because they assign better scores to lower-perplexity text, even when the text is not self-generated.
LLMs show measurable self-recognition that linearly correlates with self-preference bias in evaluations, supported by fine-tuning experiments and controls for confounders.
COSE uses LLM intrinsic confidence to weight PPO updates and prioritize replay, yielding better average performance than base models on reasoning and math benchmarks across multiple small backbones.
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.
citing papers explorer
-
AIP: A Graph Representation for Learning and Governing Agent Skills
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
-
Self-Preference Is Weak or Absent in Verifiable Instruction-Following Revision: A Four-Model Test Under Genuine Authorship
No detectable self-preference in LLMs accepting verified fixes to their own IFEval drafts versus neutral judges across four models and 85 comparisons (gap -5.1 pp, CI crossing zero).
-
Boosting Self-Consistency with Ranking
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
-
Iterative Finetuning is Mostly Idempotent
Iterative self-finetuning of LLMs mostly fails to amplify seeded behavioral traits, with amplification limited to specific DPO setups and often harming coherence.
-
Learning to Control Summaries with Score Ranking
A score-ranking loss enables controllable summarization by aligning outputs to evaluation scores, matching SOTA performance with dimension-specific control on LLaMA, Qwen, and Mistral.
-
Self-Preference Bias in Rubric-Based Evaluation of Large Language Models
Self-preference bias persists in rubric-based LLM evaluation even with fully objective, programmatically verifiable rubrics, and can shift subjective medical-chat scores by up to ~10 points.
-
Self-Preference Bias in LLM-as-a-Judge
LLMs judge their own outputs higher because they assign better scores to lower-perplexity text, even when the text is not self-generated.
-
LLM Evaluators Recognize and Favor Their Own Generations
LLMs show measurable self-recognition that linearly correlates with self-preference bias in evaluations, supported by fine-tuning experiments and controls for confounders.
-
Confidence-Orchestrated Self-Evolution against Uncertain LLM Feedback
COSE uses LLM intrinsic confidence to weight PPO updates and prioritize replay, yielding better average performance than base models on reasoning and math benchmarks across multiple small backbones.
-
MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.