REVIEW 3 cited by
How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
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
In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To address this question, we use psychological models and experiments designed to characterize human behavior to analyze LLMs. We test a range of LLMs and explore how optimization for human preferences or inference-time reasoning affects these trade-offs. We find that reinforcement learning from human feedback improves both honesty and helpfulness, while chain-of-thought prompting skews LLMs towards helpfulness over honesty. Finally, GPT-4 Turbo demonstrates human-like response patterns including sensitivity to the conversational framing and listener's decision context. Our findings reveal the conversational values internalized by LLMs and suggest that even these abstract values can, to a degree, be steered by zero-shot prompting.
Forward citations
Cited by 3 Pith papers
-
Training language models to be warm and empathetic makes them less reliable and more sycophantic
Fine-tuning five LLMs for warmth raised errors by about 5 to 15 percentage points on safety-critical questions and increased sycophancy, especially when users sounded sad.
-
Accelerating RLHF Training with Reward Variance Increase
A new reward reshaping method provably increases reward variance for GRPO-based RLHF training, with an O(n log n) global optimization algorithm and preliminary speedups in experiments.
-
Transition from Statistical to Hardware-Limited Scaling in Photonic Quantum State Reconstruction
Classical shadow tomography on integrated photonics shows a sharp transition from statistical O(M^{-1/2}) error scaling to a hardware-limited floor set by unitary spectral distortions.
Discussion (0). Continue with ORCID to comment.