HFEPX · Eval paper review
Abhinav Rajeev Kumar, Paras Chopra
Published
Sep 29, 2026
Citations
0
Trust level
High
Usefulness score
65/100 (Medium)
Extraction confidence
80% (High)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Sep 29, 2026
This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.
Use this as a practical starting point for protocol research, then validate against the original paper.
Best use
Secondary protocol comparison source
Use if you need
A benchmark-and-metrics comparison anchor.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
No major weakness surfaced.
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on their merits rather than deferring to the user. Yet the same models are far more compliant when a wrong answer is attributed to a verified source, which is how retrieval results, tool outputs, and grounded-search content often present information. We measure this gap across five open-weight families and three closed APIs. A single verified-source note endorsing a wrong answer flips 45-88% of baseline-correct responses in seven of eight models, and compliance rises with how authoritative the note sounds. Source deference and user agreement are not behaviorally interchangeable inside the model: on matched items with the same wrong answer, causal interventions can selectively suppress one without equally affecting the other. In three open-weight families, removing a fitted source direction lowers source compliance by 65-80 percentage points while removing a user or assistant direction has far smaller effects, and removing the user direction shows the reverse preference. A separately fitted intervention derived from source-versus-user cue activations moves compliance in both directions while leaving the prompt text unchanged. An authority direction fitted on trivia also transfers to PIQA and multi-turn SYCON dialogues without refitting, and removing it lowers wrong-source compliance by tens of percentage points in four of five families with no detected change in MMLU-Pro or GSM8K accuracy at our evaluation sizes. Source deference and user agreement therefore need separate evaluation.
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.
Pairwise Preference
Directly usable for protocol triage.
"Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on their merits rather than deferring to the user."
Automatic Metrics
Includes extracted eval setup.
"Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on their merits rather than deferring to the user."
Not reported
No explicit QC controls found.
"Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on their merits rather than deferring to the user."
MMLU, MMLU Pro, GSM8K, PIQA
Useful for quick benchmark comparison.
"An authority direction fitted on trivia also transfers to PIQA and multi-turn SYCON dialogues without refitting, and removing it lowers wrong-source compliance by tens of percentage points in four of five families with no detected change in MMLU-Pro or GSM8K accuracy at our evaluation sizes."
Accuracy
Useful for evaluation criteria comparison.
"An authority direction fitted on trivia also transfers to PIQA and multi-turn SYCON dialogues without refitting, and removing it lowers wrong-source compliance by tens of percentage points in four of five families with no detected change in MMLU-Pro or GSM8K accuracy at our evaluation sizes."
Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on their merits rather than deferring to the user.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
Detected: Pairwise Preference
Evaluation mode is explicit
Detected: Automatic Metrics
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: MMLU, MMLU-Pro, GSM8K, PIQA
Metric reporting is present
Detected: accuracy
