AI model builders mostly highlight unique benchmarks that act as flexible narrative tools for market positioning rather than standardized scientific measurements.
On memorization of large language models in logical reasoning
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
Prefix-RFT blends SFT and RFT via prefix sampling from demonstrations to outperform standalone SFT, RFT, and mixed-policy baselines on math reasoning problems.
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
ActivationReasoning grounds logical reasoning in LLM latent activations via SAEs to enable structured inference, concept composition, and behavior steering on multi-hop, abstraction, and safety tasks.
SIE framework automatically constructs scalable, verifiable reasoning environments from structured data, improving in-domain performance and enabling generalization to out-of-domain math and logic tasks.
GSR jointly trains LLMs to generate candidate solutions and refine a superior final answer from them, achieving state-of-the-art performance on five mathematical benchmarks while transferring across model scales.
Closed-loop self-evolution on LLMs improves reasoning on Knights and Knaves tasks but plateaus short of oracle-supervised levels, with multi-turn revision nearly matching it for large models.
PSFT modifies supervised fine-tuning by incorporating trust-region ideas from RL to constrain policy changes, yielding better out-of-domain generalization in math and human-value tasks without entropy collapse.
EKSFT masks high-entropy or high-KL tokens in low-data SFT to preserve pre-trained distribution and improve downstream RL performance on math reasoning tasks.
Combining English and target-language web retrieval boosts medical QA for low-resource languages to match high-resource performance, while English web data benefits high-resource languages most and specialized sources like PubMed lack multilingual coverage.
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.
citing papers explorer
-
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
Prefix-RFT blends SFT and RFT via prefix sampling from demonstrations to outperform standalone SFT, RFT, and mixed-policy baselines on math reasoning problems.
-
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
-
ActivationReasoning: Logical Reasoning in Latent Activation Spaces
ActivationReasoning grounds logical reasoning in LLM latent activations via SAEs to enable structured inference, concept composition, and behavior steering on multi-hop, abstraction, and safety tasks.
-
On the Generalization Gap in Self-Evolving Language Model Reasoning
Closed-loop self-evolution on LLMs improves reasoning on Knights and Knaves tasks but plateaus short of oracle-supervised levels, with multi-turn revision nearly matching it for large models.
-
Proximal Supervised Fine-Tuning
PSFT modifies supervised fine-tuning by incorporating trust-region ideas from RL to constrain policy changes, yielding better out-of-domain generalization in math and human-value tasks without entropy collapse.
-
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models
EKSFT masks high-entropy or high-KL tokens in low-data SFT to preserve pre-trained distribution and improve downstream RL performance on math reasoning tasks.
-
Effects of Cross-lingual Evidence in Multilingual Medical Question Answering
Combining English and target-language web retrieval boosts medical QA for low-resource languages to match high-resource performance, while English web data benefits high-resource languages most and specialized sources like PubMed lack multilingual coverage.
-
Sharpness-Guided Group Relative Policy Optimization via Probability Shaping
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.