跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+352新增论文
+272其中 AI 相关
+39已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 11:44 — 2026-11-17 11:44(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

24,106 已收录论文20,158 AI 相关7,049 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.17398

Alignment with Reflect-Reasoning: Learning How To Follow Principles

Henry Bell, Caroline Zhang, Dhaval Potdar, Mohammed Mobasserul Haque, Brandon Fain

原文摘要

The appropriate governing norms and principles for the alignment of Large Language Models (LLMs) often depend on cultural context and deployment application. However, most alignment techniques focus on training models to conform to human preferences or constitutional principles specified at training time and subsequently fixed. In practice, many deployers rely on system prompting to implement contextual norms and guardrails at inference time. Prior work has shown that post-generation reflective reasoning with critique and revision can improve conformance compared to simple system prompting, but such methods are limited to the reasoning abilities inherent in the trained model. We introduce Reflect-Reasoning, a training method that teaches models how to reason about alignment to principles, rather than simply which principles to follow. Across five models, Reflect-Reasoning consistently outperforms both system prompting and explicit prompting strategies for in-context reflective reasoning. These improvements extend and generalize to entirely out-of-distribution domains of medical and financial principles. We additionally demonstrate that Reflect-Reasoning reduces the occurrence of rare but serious principle violations. Finally, we show that Reflect-Reasoning does not erode the safety engineering of a model and is robust against jailbreaking attempts using adversarial constitutions. Overall, our results demonstrate that Reflect-Reasoning is a scalable method for training constitutional alignment as a generalizable reasoning capability, enabling models to adapt to novel principles and produce transparent reasoning traces without additional fine-tuning.

cs.LG

新论文 · v1arXiv:2611.16722

Mind the Accuracy-Approval Gap: How Users Evaluate Sycophantic AI in Everyday Tasks

Wajiha Naveed, Brandon Fain

原文摘要

Large language models (LLMs) often exhibit sycophancy, a tendency to agree with users, flatter or affirm them, and preserve their face, even when independent judgment or critical feedback would be more useful. Prior work has largely evaluated sycophancy through benchmark evaluations, but less is known about how users perceive and respond to sycophantic AI in everyday tasks. We combine benchmark evaluations with two large-scale user studies. We study four personas defined through system prompts: objective (instructed to prioritize accuracy over agreement), soft-sycophantic, hard-sycophantic, and baseline (no persona-specific system prompt). Benchmarks show that even baseline exhibits substantial sycophancy, agreeing with users' stated views 71.7% of the time on NLP Survey, compared with 54.8% for objective and 89.5% for hard-sycophantic. Under conversational pressure on TruthfulQA, accuracy ranged from 81.9% for objective to 59.6% for baseline and 8.7% for hard-sycophantic. Participants were assigned to one of the four personas, and either discussed contested policy topics or collaborated with AI on email writing. Despite its higher accuracy under pressure, objective AI was rated significantly less respectful and satisfying than the other personas, and less trustworthy than baseline. Baseline and sycophantic personas did not differ significantly. Persona did not significantly affect how often participants changed their opinions, although participants who discussed with objective AI had greater odds of reduced confidence. Objective AI prompted greater writing expansion than soft-sycophantic AI, but final writing quality did not differ significantly across personas. These findings highlight a tension between accuracy and user approval: personas with substantially lower accuracy under conversational pressure received more favorable ratings for respect and satisfaction than objective AI.

cs.AI

版本更新 · v2arXiv:2611.10045

Don't Blame The Preferences: Examining The Emergence of Sycophancy in LLM Training

Chao Peter Yang, Catherine Zehr, Pranav Bijith, Brandon Fain

原文摘要

AI sycophancy, the tendency of large language models (LLMs) to flatter users and affirm their beliefs, can undermine accuracy and contribute to misinformation, dependence, and overconfidence. Although prior work has benchmarked sycophancy in released models and proposed mitigations, its origins during training remain poorly understood. Preference alignment methods such as RLHF and DPO are often blamed, but their effects are rarely compared with earlier training stages. We investigate sycophancy across the training pipelines of three model families and three benchmarks. We find that sycophancy is largely established by the end of supervised fine-tuning (SFT), rather than introduced by preference alignment. Across all nine model benchmark combinations, SFT checkpoints attain at least 92% of preference aligned models' sycophancy scores and at least 85% of final models' scores; on average, they are about as sycophantic as final models. Preference alignment increases sycophancy in only four of nine cases, by an average of 4.2 percentage points when it does. To probe the underlying causes, we isolate model representations associated with sycophancy using mechanistic interpretability and measure their activation on training datasets from each stage. SFT datasets show roughly the same average activation as other training data but contribute substantially more examples, and the highest-scoring individual datasets all come from SFT. Our findings suggest that addressing sycophancy requires interventions throughout the training pipeline, particularly in data selection and augmentation for pre-training and SFT.

cs.AI