AI Paper Atlas

Research map / Large language models / Alignment and preferences

When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice

Dean Ariel, Guy Laban

NeurIPS 2026 · Large language models › Alignment and preferences · approach: LLM-as-judge and feedback data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Defines goal displacement in LLM advice (warmth or reassurance substituting for goal-advancing content) and releases GDB, a 230-scenario benchmark for measuring it.

Problem

Conversational LLMs deployed for advice may replace actionable, goal-advancing content with emotional warmth, reassurance, or non-directive encouragement even when these do not satisfy the user's objective.

Approach

Formalizes goal displacement as a failure mode distinct from general sycophancy or empathy, and operationalizes it in a benchmark of advice scenarios where warmth alone cannot satisfy the user's goal.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use newer model generation within the same vendor (GPT-4o-mini to GPT-5.4-mini)GPT-4o-mini · GDB trap scenariostrap displacement rate (%): 32.3% -> 2.3%Improved
use newer model generation (GPT-4o to GPT-5.4)GPT-4o · GDB trap scenariostrap displacement rate (%): 17.0% -> 0.0%Improved
add SFT to OLMo-2 Base (ablation)OLMo-2 7B · GDB F2displacement rate (%): 52.3% -> 52.3%No clear effect
add DPO after SFT (ablation)OLMo-2 7B · GDB F2displacement rate (%): 52.3% -> 13.8%Improved
add SFT then DPO to Base (ablation)OLMo-2 7B · GDB traptrap displacement rate (%): 30.8% -> 7.7%Improved
instruction tuning of base model (ablation)Qwen 2.5 · GDB traptrap displacement rate (%): 26.9% -> 6.9%Improved
move from Mistral v0.2 to v0.3Mistral 7B · GDB traptrap displacement rate (%): 14.6% -> 6.9%Improved
scale open-weight models from <=8B to >=32Bopen-weight models · GDB F2displacement rate (%): 33.3 -> 15.4%Improved
scale open-weight models from <=8B to >=32Bopen-weight models · GDB F0 reverse displacementreverse displacement rate (%): 31.7% -> 25.7%No clear effect
higher capability (Arena Elo)18 LLMs · GDB trap scenariostrap displacement vs Arena Elo (Spearman rho): rho = -0.706Improved
add social pressure at fixed complexity (ablation)factorial probe, 8 models · sycophancy probesycophancy rate: +66.3 and +48.8 percentage pointsHurt
add social pressure at fixed complexity (ablation)factorial probe, 8 models · sycophancy probedisplacement rate: +2.5 and 0.0 pointsNo clear effect

Experimental setup

Datasets: GDB

Benchmarks: GDB

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy