HFEPX · Eval paper review
Rulin Shao, Shuyue Stella Li, Rui Xin, Scott Geng +10 more
Published
Jun 12, 2025
Citations
0
Trust level
Low
Usefulness score
0/100 (Low)
Extraction confidence
25% (Low)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Feb 25, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this as background context only. Do not make protocol decisions from this page alone.
All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.
Best use
Background context only
Use if you need
Background context only.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
This paper looks adjacent to evaluation work, but not like a strong protocol reference.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer. For example, RLVR training with GRPO improves MATH-500 performance for Qwen2.5-Math-7B by 21.4 percentage points using randomly assigned rewards, nearly matching the 29.1-point gain from ground-truth rewards. To explain this counterintuitive observation, we show that GRPO exhibits a clipping bias from the clip term, which can amplify high-prior behaviors learned during pretraining even without informative rewards. As a case study, we identify one such behavior in Qwen2.5-Math models, which we call code reasoning -- reasoning in code without actual code execution; code-reasoning frequency increases from 65 percent to over 90 percent with spurious rewards. However, the presence of such amplifiable behaviors is highly model-dependent. In practice, spurious rewards that are effective for Qwen models often fail to produce gains for other model families, such as Llama3 or OLMo2. Our results highlight the importance of validating RL methods across diverse models rather than relying on a single de facto choice: large gains can arise on Qwen models even from random rewards that do not reflect genuine capability improvements.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
None explicit
No explicit feedback protocol extracted.
"We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer."
None explicit
Validate eval design from full paper text.
"We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer."
Not reported
No explicit QC controls found.
"We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer."
MATH 500
Useful for quick benchmark comparison.
"For example, RLVR training with GRPO improves MATH-500 performance for Qwen2.5-Math-7B by 21.4 percentage points using randomly assigned rewards, nearly matching the 29.1-point gain from ground-truth rewards."
Not extracted
No metric anchors detected.
"We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer."
No metric terms were extracted from the available abstract.
We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
No explicit human feedback protocol detected.
Evaluation mode is explicit
No clear evaluation mode extracted.
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: MATH-500
Metric reporting is present
No metric terms extracted.
