Hugging Face Trending Papers
Hearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Oct 21
Hearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates
arXiv:2610.27745v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judgment assistants and as stand-in participants in psychology experiments, yet little is known...
arXiv Computation and Language
Oct 8
The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets in Large Language Models
The study investigates whether large language models (LLMs) that allocate extra computation during inference—termed reasoning models—reduce classic decision biases compared to their non‑reasoning counterparts. Using 30 vignettes covering six cognitive biases and varying token budgets up to 8,192 tokens, the authors find that reasoning models are not less biased, and increased deliberation does not reliably diminish bias magnitude. Only anchoring showed a bias in the human direction, while other biases either remained unchanged or moved further from human patterns, suggesting that test‑time reasoning does not guarantee rationality.
arXiv AI
Oct 16
Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
arXiv AI
Oct 7
How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation
arXiv:2610.08514v1 Announce Type: new Abstract: Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the tran...
arXiv Computation and Language
Sep 18
Message capacity and claim wording set the transition points of collective truth-finding in language-model networks
The study investigates how limited reading capacity and claim wording influence consensus outcomes in language‑model networks. By modeling message capacity as the number of messages an agent reads, the authors show that when agents read fewer than about 6.4 messages on average, a wrong consensus becomes unreachable. However, the wording of a claim—its inherent threshold—can override this effect, leading to incorrect consensus even when most agents start correct.
arXiv AI
Sep 10
A Layered Analysis of Disagreement And Answer Quality in Multi-Agent LLM Debate
arXiv:2609.08016v1 Announce Type: new Abstract: Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagre...