Anchor-guided variance-aware reward modeling uses two response-level anchors to resolve non-identifiability in Gaussian models of pluralistic preferences, yielding provable identification, a joint training objective, and improved RLHF performance.
hub
Reward shaping to mitigate reward hacking in rlhf
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
LPA uses fewer than 100 personality trait statements to train LLMs for harmlessness, matching the robustness of methods using 150k+ harmful examples while generalizing better to new attacks.
Introduces the first benchmark for fine-grained failures in reinforcement fine-tuning of LLMs and an automatic management framework that detects, diagnoses, and remediates them.
UARM equips reward models with quantile-based conformal prediction uncertainty and reweights GRPO advantages via heteroscedastic variance decomposition to improve calibration and reduce reward hacking in RLHF.
The LLM-as-Environment-Engineer framework lets the policy model redesign its own RL environments on the new MAPF-FrozenLake testbed, outperforming larger models and fixed baselines with Qwen3-4B.
CoT SFT disrupts long-range routing in hybrid models via changes to W_Q and W_K; QK-Restore restores pre-SFT projections to recover NIAH performance.
GraphAE builds graphs from RM hidden-state similarities among sampled responses and propagates advantages to improve RLHF sample efficiency.
GPRL carries a k-dimensional skew-symmetric preference structure into policy updates with per-dimension advantages and a drift monitor, yielding 56.51% length-controlled win rate on AlpacaEval 2.0 from Llama-3-8B-Instruct while outperforming SimPO and SPPO on other benchmarks.
Training-inference mismatch in separated rollout and optimization stages of LLM RL can independently cause training collapse.
Rubric-based RL verifiers can be gamed via partial criterion satisfaction and implicit-to-explicit tricks, yielding proxy gains that do not improve quality under rubric-free judges; stronger verifiers reduce but do not eliminate the mismatch.
SelectiveRM applies optimal transport with a joint consistency discrepancy and partial mass relaxation to produce reward models that optimize a tighter upper bound on clean risk while autonomously dropping noisy preference samples.
A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
OPERA uses perplexity dynamics as intrinsic rewards for RL alignment on open-ended tasks, synthesizes a 20k trajectory dataset via guiding words and log-prob rollouts, and sets new SOTA on Qwen3-8B matching some proprietary models.
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.
EqLen reframes length bias in sequence-level RL as a comparison-unit construction problem and builds equal-length training segments via dual-track generation, prefix inheritance, and segment masking.
Vision SR1 decomposes VLM reasoning into visual and language components and uses internal self-rewards to improve visual reasoning and reduce hallucinations more efficiently than external-supervision methods.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.