REVIEW 9 cited by
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
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
Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but unhelpful responses only due to their length). To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful. Specifically, our 37k-sample dataset has annotations for correctness, coherence, complexity, and verbosity in addition to overall helpfulness of responses. Training Llama 2 70B using the HelpSteer dataset with SteerLM technique produces a model that scores 7.54 on MT Bench, which is currently the highest score for open models that do not require training data from more powerful models (e.g. GPT4). We release this dataset with CC-BY-4.0 license at https://huggingface.co/datasets/nvidia/HelpSteer
Forward citations
Cited by 9 Pith papers
-
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
MAHALO aligns LLMs to multiple objectives in one model via per-objective action heads and PRM-guided decoding, improving math, value, and tutoring metrics jointly.
-
Adaptive Margin RLHF via Preference over Preferences
Adaptive margins for DPO inferred from preference-over-preference comparisons improve alignment quality, with random sampling of comparisons working best overall.
-
Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
Jointly training a Bradley-Terry preference head and a multi-attribute regression head on a shared embedding improves reward-model robustness to reward hacking and boosts multi-objective scoring performance.
-
PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
PersonaFeedback provides a human-labeled benchmark showing current LLMs, including strong reasoners, score only about 65-70 percent on hard personalization choices, and explicit persona information helps more than retrieval.
-
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
A new 8TB openly-licensed text corpus trains 7B LLMs that are competitive with Llama 1/2, showing that performant models need not depend on unlicensed web data.
-
Typhoon T1: An Open Thai Reasoning Model
Structured long-thinking SFT turns a 3B Thai instruct model into a reasoning model that improves on several English benchmarks and can think in Thai, with a fully open recipe.
-
T-POP: Test-Time Personalization with Online Preference Feedback
T-POP uses dueling-bandit token selection to learn a reward function online from pairwise user feedback, enabling test-time personalization of a frozen LLM without fine-tuning.
-
Towards Reliable, Uncertainty-Aware Alignment
Variance-aware RLHF adds a variance-weighted KL penalty to PPO and reduces reward variance and the risk of underperforming the reference policy in the paper's experiments.
-
Reward Reasoning Model
Reward models that think before judging, trained via reinforcement learning without human-written reasoning traces, outperform standard reward models and improve with more test-time compute.
Discussion (0). Continue with ORCID to comment.