AI Paper Atlas

Research map / Large language models / AI and society

Using cognitive models to reveal value trade-offs in language models

Sonia Krishna Murthy, Rosie Zhao, Jennifer Hu, Sham M. Kakade, Markus Wulfmeier, Peng Qian, Tomer Ullman

ICLR 2026 · Large language models › AI and society · approach: Critiques of LLM claims and judging

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add low or medium reasoning effortclosed-source LLMs · Polite speech taskprojected informational mixture phi: beta_low = 0.228, beta_medium = 0.211Improved
increase reasoning effort from low to mediumclosed-source LLMs · Polite speech taskphiNo clear effect
prompt for social goalclosed-source LLMs · Polite speech taskw_pre, w_inf, phiMixed
prompt for informative goalclosed-source LLMs · Polite speech taskw_inf and phiImproved
use Claude-Sonnet-3.7 low reasoning instead of Claude-Sonnet-3.5 no reasoningClaude · Polite speech taskw_inf: t = -5.49, p = 0.005Improved
add reasoning to Gemini-FlashGemini-Flash · Polite speech taskw_inf, w_soc, w_pre: p = 0.43 for w_inf, p = 0.20 for w_soc, p = 0.89 for w_preNo clear effect
use UltraFeedback instead of HH-RLHF as feedback dataset (ablation)Qwen and Llama aligned with DPO/PPO · Polite speech taskw_infImproved
use HH-RLHF instead of UltraFeedback (ablation)Qwen and Llama aligned with DPO/PPO · Polite speech taskw_socImproved
use PPO instead of DPO (ablation)Qwen and Llama · Polite speech taskphi: approx. 0.7Mixed
use Qwen-Instruct instead of Llama-Instruct base (ablation)open-source alignment · Polite speech taskw_inf, w_preMixed

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