HER trains LLMs on reverse-engineered reasoning data and human preference rewards to improve cognitive persona simulation, reporting 30-point gains on CoSER and 15% on Minimax benchmarks over Qwen3-32B.
BooookScore : A systematic exploration of book-length summarization in the era of LLMs
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
WiCER iteratively diagnoses and repairs fact loss during wiki compilation for LLMs, recovering 80% of quality lost in blind distillation across 17 domains while cutting catastrophic failures by 55%.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
ThreadSumm improves structured summarization of nested discourse threads by combining LLM-based aspect and content unit extraction with sentence ordering and Tree of Thoughts search for better coherence and opinion coverage.
CheckSupport uses local LLMs with staged prompting to recommend and complete reporting checklists for manuscripts, reporting 90% recommendation accuracy and 88% item-level completion accuracy on peer-reviewed papers.
citing papers explorer
-
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
HER trains LLMs on reverse-engineered reasoning data and human preference rewards to improve cognitive persona simulation, reporting 30-point gains on CoSER and 15% on Minimax benchmarks over Qwen3-32B.
-
WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems
WiCER iteratively diagnoses and repairs fact loss during wiki compilation for LLMs, recovering 80% of quality lost in blind distillation across 17 domains while cutting catastrophic failures by 55%.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts
ThreadSumm improves structured summarization of nested discourse threads by combining LLM-based aspect and content unit extraction with sentence ordering and Tree of Thoughts search for better coherence and opinion coverage.
-
CheckSupport: A Local LLM-Powered Tool for Automated Manuscript Submission Checklist Selection and Completion
CheckSupport uses local LLMs with staged prompting to recommend and complete reporting checklists for manuscripts, reporting 90% recommendation accuracy and 88% item-level completion accuracy on peer-reviewed papers.