Small 7B reasoning models were fine-tuned on synthetic and curated QFT problems using RL and SFT, yielding performance gains, error analysis, and public release of data and traces.
LoRA without regret
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 10roles
background 3polarities
background 3representative citing papers
Benign multilingual fine-tuning causes language-specific safety drifts with adversarial compliance rates rising up to four-fold, decoupled from capability gains.
Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
Dr. Post-Training reframes general data as a data-induced regularizer for LLM post-training updates, yielding a family of methods that outperform data-selection baselines on SFT, RLHF, and RLVR tasks.
CASCADE enables LLMs to continually adapt at deployment via case-based episodic memory and contextual bandits, improving macro-averaged success by 20.9% over zero-shot on 16 tasks spanning medicine, law, code, and robotics.
AutoOR uses synthetic data generation and RL post-training with solver feedback to enable 8B LLMs to autoformalize linear, mixed-integer, and non-linear OR problems, matching larger models on benchmarks.
Empirical scaling laws for task-specific LLM distillation in quantitative finance indicate that chain-of-thought supervision recovers general knowledge lost during iterative pruning while in-domain performance degrades predictably.
RLVR exhibits implicit reward overfitting to training data and optimizes heavy-tailed singular spectra with rank-1 focus on reasoning capability.
A 14B model trained on synthetic data from Brazilian clinical guidelines outperforms larger LLMs on new benchmarks for Brazilian healthcare protocols.
citing papers explorer
-
Fine-Tuning Small Reasoning Models for Quantum Field Theory
Small 7B reasoning models were fine-tuned on synthetic and curated QFT problems using RL and SFT, yielding performance gains, error analysis, and public release of data and traces.
-
The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
Benign multilingual fine-tuning causes language-specific safety drifts with adversarial compliance rates rising up to four-fold, decoupled from capability gains.
-
PreFT: Prefill-only finetuning for efficient inference
Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.
-
Not How Many, But Which: Parameter Placement in Low-Rank Adaptation
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
-
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
Dr. Post-Training reframes general data as a data-induced regularizer for LLM post-training updates, yielding a family of methods that outperform data-selection baselines on SFT, RLHF, and RLVR tasks.
-
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
CASCADE enables LLMs to continually adapt at deployment via case-based episodic memory and contextual bandits, improving macro-averaged success by 20.9% over zero-shot on 16 tasks spanning medicine, law, code, and robotics.
-
AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems
AutoOR uses synthetic data generation and RL post-training with solver feedback to enable 8B LLMs to autoformalize linear, mixed-integer, and non-linear OR problems, matching larger models on benchmarks.
-
Scaling Laws for Task-Specific LLM Distillation
Empirical scaling laws for task-specific LLM distillation in quantitative finance indicate that chain-of-thought supervision recovers general knowledge lost during iterative pruning while in-domain performance degrades predictably.
-
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
RLVR exhibits implicit reward overfitting to training data and optimizes heavy-tailed singular spectra with rank-1 focus on reasoning capability.
-
Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines
A 14B model trained on synthetic data from Brazilian clinical guidelines outperforms larger LLMs on new benchmarks for Brazilian healthcare protocols.