5arXiv cs.CL (Computation and Language)·
Groc-PO: Grounded Context Preference Optimization reduces hallucination in multimodal LLMs
Researchers introduce Groc-PO, a preference optimization framework for multimodal LLMs that applies stage-specific supervision across object grounding, contextual grounding, and grounded reasoning stages, rather than only at the final-answer level as in standard DPO. The method is paired with a new dataset (GCPD) organized around these three grounding stages. Experiments show improvements over standard DPO and other baselines on hallucination mitigation and faithful reasoning, addressing the credit-assignment problem where early grounding errors propagate through reasoning chains.
Related guides (3)
Related events (8)
GraphPO: Graph-based Policy Optimization reduces redundancy in LLM reasoning RL
GraphPO is a new reinforcement learning framework that represents reasoning rollouts as directed acyclic graphs rather than independent chains or trees, merging semantically equivalent reasoning paths into equivalence classes to share suffixes and reduce redundant exploration. The approach assigns efficiency advantages to incoming edges and correctness advantages to outgoing edges, deriving process supervision from outcome rewards. Experiments on three LLMs across reasoning and agentic search benchmarks show consistent improvements over chain- and tree-based baselines under equal token or response budgets. The method also provides theoretical guarantees on reduced advantage-estimation variance.
Gravity-Weighted DPO enforces multi-level instruction hierarchies in LLMs
Researchers introduce Gravity-Weighted DPO (GW-DPO), a preference-optimization objective that scales per-sample loss offsets by the structural distance between conflicting instruction levels, addressing the problem of uniform architectural privilege across trust levels in production LLMs. The work formalizes a 5-level instruction hierarchy with ten pairwise priority relations and combines GW-DPO with hierarchy-specific delimiter tokens and Instructional Segment Embeddings (ISE). Evaluated on Llama-3.1-8B-Instruct, the bilateral GW-DPO schedule Pareto-improves over standard DPO on macro pairwise priority adherence while cutting over-refusal rates in half. The approach directly targets prompt injection vulnerabilities arising from models' inability to resolve competing instructions by privilege level.
ContextRL: Context-aware reinforcement learning improves grounding in agentic and multimodal LLMs
Researchers introduce ContextRL, a reinforcement learning method that trains LLMs to select the context that supports a given query-answer pair from two highly similar candidates, rather than supervising only final answers. The approach constructs contrastive context pairs in two domains: coding agent trajectories (1k pairs) and multimodal image pairs (7k pairs). ContextRL achieves +2.2% average gains over standard GRPO on 5 long-horizon benchmarks and +1.8% across 12 visual QA benchmarks, with ablations showing the gains stem from the context-selection objective rather than the contrastive data alone.
Preference Optimization for Vision Language Models
This Hugging Face blog post covers the application of Direct Preference Optimization (DPO) to vision-language models (VLMs). It likely discusses how preference learning techniques originally developed for text-only LLMs can be adapted to multimodal settings. The post addresses training methodology for aligning VLMs with human preferences across both visual and textual modalities.
LamPO: Lambda-Style Policy Optimization with Pairwise Decomposed Advantage for Reasoning LMs
LamPO proposes a new RLVR training objective that replaces GRPO's scalar group-relative advantages with a Pairwise Decomposed Advantage, aggregating pairwise reward gaps within response groups and weighting comparisons by confidence-aware log-probability differences. The method retains a critic-free, clipped-update PPO-style structure and optionally adds a ROUGE-L-based dense auxiliary reward to reduce sparsity. Experiments on AIME24, AIME25, MATH-500, and GPQA-Diamond using Qwen3-1.7B, Qwen3-4B, and Phi-4-mini show consistent improvements over GRPO and other RLVR variants with more stable training dynamics.
N-GRPO: Semantic Neighbor Mixing for Improved Policy Optimization in LLM Reasoning
A new arXiv preprint introduces N-GRPO, an exploration strategy for the GRPO reinforcement learning framework that improves solution diversity during rollout by mixing embeddings of anchor tokens with their nearest semantic neighbors rather than using token-level sampling or random noise. The method is evaluated on DeepSeek-R1-Distill-Qwen models of various sizes and shows consistent improvements on math reasoning benchmarks plus out-of-distribution generalization. The work targets a known limitation in RLHF-style training: redundant rollout trajectories that reduce effective learning signal.
Preference Tuning LLMs with Direct Preference Optimization Methods
A Hugging Face blog post surveys Direct Preference Optimization (DPO) and related preference tuning methods for aligning large language models. The post covers the landscape of DPO variants and their practical application via the TRL library. It serves as a technical reference for practitioners implementing RLHF alternatives.
PGT: Procedurally Generated Tasks for Improving Visual Grounding in MLLMs
This paper introduces Procedurally Generated Tasks (PGT), a data-driven framework that overlays geometric primitives on images to create dense supervision signals for fine-grained visual grounding in multimodal large language models. PGT serves both as a training augmentation method and a diagnostic tool to isolate perception failures from semantic priors. Instruction tuning on LLaVA-v1.5-Instruct augmented with PGT data yields gains of up to +20% on the What'sUp benchmark and +13.3% on CV-Bench-2D. The results suggest that spatial reasoning deficits in MLLMs stem primarily from inadequate supervision rather than architectural or resolution constraints.