REVIEW 9 cited by
Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout the fine-tuning process remains a significant challenge, as resolving conflicts between safety and helpfulness can be non-trivial. Typically, the safety alignment of LLM is trained on data with safety-related categories. However, our experiments find that naively increasing the scale of safety training data usually leads the LLMs to an ``overly safe'' state rather than a ``truly safe'' state, boosting the refusal rate through extensive safety-aligned data without genuinely understanding the requirements for safe responses. Such an approach can inadvertently diminish the models' helpfulness. To understand the phenomenon, we first investigate the role of safety data by categorizing them into three different groups, and observe that each group behaves differently as training data scales up. To boost the balance between safety and helpfulness, we propose an Equilibrate RLHF framework including a Fine-grained Data-centric (FDC) approach that achieves better safety alignment even with fewer training data, and an Adaptive Message-wise Alignment (AMA) approach, which selectively highlight the key segments through a gradient masking strategy. Extensive experimental results demonstrate that our approach significantly enhances the safety alignment of LLMs while balancing safety and helpfulness.
Forward citations
Cited by 9 Pith papers
-
Step-Level Preference Learning for Generative Agents in Social Simulations
Step-level human preference data collected via SimPref, then SFT+DPO, improves long-horizon social-simulation behavior of open-weight LLM agents on held-out events.
-
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
A two-stage Safe-SFT + Safe-GDPO training framework reduces personalized safety violations in conversational movie and game recommendation to near-zero on the authors' new SafeRec benchmark.
-
Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
HC-RLHF returns an aligned language model only after a held-out safety test certifies, with probability at least 1-delta, that expected harm (as judged by a learned cost model) is below a chosen threshold.
-
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
A new benchmark shows that top reasoning models identify all relevant risks in under 40% of cases even when their final answers look safe.
-
USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
USB-SafeBench is a unified MLLM safety benchmark with 61 risk categories, 4 modality combinations, and dual-language vulnerability and oversensitivity tests.
-
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
Dualizing Safe RLHF yields a one-dimensional convex calibration of λ that defines a drop-in safety-aware reward for Best-of-N and token-level inference-time decoders.
-
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
A unified benchmark comparing RAG knowledge-extraction attacks and defenses, showing query diversity boosts extraction, embedding attacks fail to transfer, and graph indexing raises per-token leakage.
-
Get Experience from Practice: LLM Agents with Record & Replay
AgentRR is a proposed paradigm that records agent traces, generalizes them into multi-level experiences, and replays them under safety checks to make LLM agents cheaper, faster, and more reliable.
-
Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI
A survey of reinforcement learning in healthcare that frames RL as a paradigm shift from prediction to agentive clinical intelligence.
Discussion (0). Sign in to comment.