TABOM is a trajectory-aligned Boltzmann modeling framework that turns self-distilled inference paths into a pairwise ranking loss to close the training-inference gap in diffusion language models and expand their effective capabilities.
hub
Measuring mathematical problem solving with the math dataset
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
dataset 3
background 1
citation-polarity summary
representative citing papers
GenAC introduces generative critics with chain-of-thought reasoning and in-context conditioning to improve value approximation and downstream RL performance in LLMs compared to value-based and value-free baselines.
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
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.
Doubly robust estimators that incorporate low-rank predictions enable valid finite-sample confidence intervals for best-model identification under adaptive sampling and without-replacement example selection in LLM evaluation.
RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.
SPaCe uses semantic clustering to shrink training sets and a multi-armed bandit to adaptively select samples, matching or beating baselines on reasoning benchmarks with up to 100x fewer examples.
RewardBench 2 is a new benchmark that supplies challenging fresh human prompts for reward model evaluation, yielding lower average scores but higher correlation with downstream best-of-N sampling and RLHF training performance.
Entropy minimization on self-generated outputs elicits strong reasoning in pretrained LLMs, matching or exceeding supervised RL methods on benchmarks.
ToRA trains language models on interactive tool-use trajectories with imitation learning and output shaping to integrate reasoning and external tools, yielding 13-19% gains on math datasets and new highs like 44.6% on MATH for a 7B model.
ReAD applies a contextual bandit to allocate fixed-token distillation budget across interdependent LLM capabilities, yielding higher task utility and fewer negative spillovers than standard methods.
citing papers explorer
-
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
-
Emergent Slow Thinking in LLMs as Inverse Tree Freezing
RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.