Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
super hub Canonical reference
Training language models to follow instructions with human feedback
Canonical reference. 93% of citing Pith papers cite this work as background.
262
Pith papers citing it
Background
93% of classified citations
abstract
Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these models are not aligned with their users. In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback. Starting with a set of labeler-written prompts and prompts submitted through the OpenAI API, we collect a dataset of labeler demonstrations of the desired model behavior, which we use to fine-tune GPT-3 using supervised learning. We then collect a dataset of rankings of model outputs, which we use to further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT. In human evaluations on our prompt distribution, outputs from the 1.3B parameter InstructGPT model are preferred to outputs from the 175B GPT-3, despite having 100x fewer parameters. Moreover, InstructGPT models show improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets. Even though InstructGPT still makes simple mistakes, our results show that fine-tuning with human feedback is a promising direction for aligning language models with human intent.
hub tools
citation-role summary
background 54
method 1
other 1
citation-polarity summary
claims ledger
- abstract Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these models are not aligned with their users. In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback. Starting with a set of labeler-written prompts and prompts submitted through the OpenAI API, we collect a dataset of labeler demonstrations of the desired model behavior, which we u
authors
co-cited works
representative citing papers
KV cache quantization silently erodes LLM safety alignment via vulnerable low-dimensional subspaces, diagnosed by Per-Channel Reduction into three failure modes and mitigated training-free with up to 97% recovery.
RefusalBench shows strict refusal rates fail to rank frontier LLMs correctly on biological safety, with provider effects and partial-compliance patterns that binary metrics miss.
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.
Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average across models and datasets.
Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.
Controlled student-teacher experiments across four benchmarks show interactive gains are driven more by the student's ability to use feedback than by teacher quality, with self-feedback adding little beyond unguided retries.
TRL extends tandem training to RLVR pipelines, matching GRPO solo reasoning on Qwen3-4B math tasks while improving handoff robustness, reducing distributional drift, and increasing CoT legibility for the junior.
A reliable-to-expressive curriculum with dynamic rubrics trains a 12B safety judge to achieve 94%+ accuracy with only 0.76 cross-rubric variance on three different rubric prompts.
OPD updates occupy a relaxed off-principal regime and rapidly lock into a low-dimensional subspace that is functionally sufficient for its performance, distinct from SFT and RLVR trajectories.
LLM judges exhibit high stability under neutral re-evaluation but substantial reversibility under targeted post-decision challenges, quantified via a new Evaluation Robustness Score (ERS).
TTT-RTL performs per-design test-time RL on an LLM policy with EDA-derived PPA rewards and an adaptive KL controller, reducing geometric-mean PPA product by 65.1% on RTLLM v2.0 and ADP by 59.4% on an industrial FPU unit.
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
Low-resource safety failures are action failures because the harmfulness representation transfers but the decision calibration does not; this is fixed by recalibrating a high-resource gate with 1-4 target-language examples.
EST-PRM stress-tests five PRM models on 4,687 reasoning chains from MATH-500, GSM8K, and PRMBench using three label-preserving transformations and reports model-specific vulnerability patterns.
Introduces (ε,q,t,A)-behavioral indistinguishability and shows via Qwen/Llama experiments that LoRA distillation boosts semantic similarity but leaves detectable behavioral differences under adversarial evaluation.
A hybrid first-order then zeroth-order optimization approach improves robustness of safety-aligned LLMs while preserving utility, with layer-wise sensitivity estimation for efficiency.
Sampling 20,000 stories shows 11 words dominate LLM outputs across models, linked to preference data and demonstrating alignment's disproportionate effect on diversity.
BC Protocol uses dual-expert structured dialogue to elicit more natural CoT than solo expert writing, demonstrated by large gains in naturalness ratings in a controlled fiction-domain experiment.
SELECT-LLM is the first active model selection framework for LLMs that uses expected information gain from pairwise output similarities to minimize required annotations, reporting up to 84.78% cost reduction across 23 datasets and 156 models.
Distribution-Aware Reward optimizes LLM regression by treating rollouts as empirical predictive distributions and rewarding marginal improvements in CRPS quality rather than point accuracy alone.
citing papers explorer
-
What Drives Interactive Improvement from Feedback?
Controlled student-teacher experiments across four benchmarks show interactive gains are driven more by the student's ability to use feedback than by teacher quality, with self-feedback adding little beyond unguided retries.
-
Tandem Reinforcement Learning with Verifiable Rewards
TRL extends tandem training to RLVR pipelines, matching GRPO solo reasoning on Qwen3-4B math tasks while improving handoff robustness, reducing distributional drift, and increasing CoT legibility for the junior.
-
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
A reliable-to-expressive curriculum with dynamic rubrics trains a 12B safety judge to achieve 94%+ accuracy with only 0.76 cross-rubric variance on three different rubric prompts.
-
Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges
LLM judges exhibit high stability under neutral re-evaluation but substantial reversibility under targeted post-decision challenges, quantified via a new Evaluation Robustness Score (ERS).
-
AIP: A Graph Representation for Learning and Governing Agent Skills
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
-
Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization
A hybrid first-order then zeroth-order optimization approach improves robustness of safety-aligned LLMs while preserving utility, with layer-wise sensitivity estimation for efficiency.
-
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
-
Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor
Political bias audits of LLMs largely capture sycophantic accommodation to the inferred political identity of the asker rather than any fixed model ideology.
-
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
HiPO improves LLM reasoning performance by optimizing preferences separately on response segments rather than entire outputs.
-
Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception
Springdrift provides an auditable persistent runtime for long-lived LLM agents with case-based memory, normative safety gating, and ambient self-perception, shown in a 23-day single-instance deployment where the agent self-diagnosed bugs and maintained cross-channel context.
-
ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation
ContractEval benchmark on 364 tasks shows code LLMs achieve 75-82% functional pass@1 but 0% contract satisfaction under standard prompting, rising only to 23-41% with explicit contracts.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
A Generalist Agent
Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.
-
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.
-
Towards Human-Level Book-Writing Capability
A supervised fine-tuning approach using inverted multi-resolution planning scaffolds from public-domain novels trains models to generate book-length stories with more human-like literary qualities than standard instruction-tuned LLMs.
-
Iterative Finetuning is Mostly Idempotent
Iterative self-finetuning of LLMs mostly fails to amplify seeded behavioral traits, with amplification limited to specific DPO setups and often harming coherence.
-
Pioneer Agent: Continual Improvement of Small Language Models in Production
Pioneer Agent automates the full lifecycle of adapting and continually improving small language models via diagnosis-driven data synthesis and regression-constrained retraining, delivering gains of 1.6-83.8 points on benchmarks and large lifts in production-style tasks.
-
Teaching an Agent to Sketch One Part at a Time
A multi-modal LM agent is trained to produce vector sketches part-by-part via supervised fine-tuning and process-reward RL on the new ControlSketch-Part dataset with automatic part annotations.
-
Towards an AI co-scientist
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
DEPS combines LLM-based interactive planning with a trainable goal selector to create a zero-shot multi-task agent that completes 70+ Minecraft tasks and nearly doubles prior performance.
-
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
The Flan Collection demonstrates that task balancing, data enrichment, and mixed prompt training are critical to effective instruction tuning, yielding stronger Flan-T5 models released publicly.
-
AI Native Games: A Survey and Roadmap
The paper proposes a counterfactual definition of AI-native games, screens 53 examples, introduces a G/N taxonomy, and outlines a research roadmap for the field.
-
POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation
POTracker fine-tunes an LLM with POTrackerLoss combining textual and structural similarity, achieving up to 86.47% structural accuracy on 1,000 power outage reports and outperforming baselines by up to 51%.
-
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
CICL scores and compresses context evidence for LLM agents via action-shift and outcome-uplift metrics, lifting hit@1 from 0.58 to 0.78 on 50 SWE-bench retrieval tasks.
-
Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
Introduces the Gumbel Machine and β-Hindsight control algorithm to generate rubric-consistent counterfactual student writing similar to a given reference text.
-
ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking
ECPO is a listwise policy optimization method that couples ranking utility with span-level evidence certificate validity and a deterministic verifier reward on MAVEN-ERE and RAMS datasets.
-
Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities
Absurd World automatically converts real-world problems into absurd yet logically coherent scenarios to test whether LLMs can reason without depending on familiar patterns.
-
Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis
Agent Mentor analyzes semantic trajectories in agent logs to identify undesired behaviors and derives corrective prompt instructions, yielding measurable accuracy gains on benchmark tasks across three agent setups.
-
MIRROR: Converging Cognitive Principles as Computational Mechanisms for AI Reasoning
MIRROR applies cognitive principles of parallel processing, reconstructive synthesis, and complementary learning to AI, yielding 21% relative gains on multi-turn constraint-maintenance tasks across seven models with supporting ablations.
-
A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI
Proposes a state-space constrained emulation framework for pluralistic AI evaluation using synthetic cognitive profiles and reports instability in persona coherence under sequential and perturbed inference.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
A fine-tuned 4B model matches or exceeds frontier LLMs in terminal execution subagent tasks for coding agents, reducing main agent token usage by 30% with no performance loss.
-
AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
AEM adaptively modulates response-level entropy in agentic RL to improve credit assignment and exploration-exploitation balance, yielding gains on ALFWorld, WebShop, and SWE-bench.
-
Preference Learning for AI Alignment: a Causal Perspective
Advocates applying causal inference to preference learning for LLM alignment to diagnose generalization failures and guide better data practices.
-
Position: Hippocampal Explicit Memory Is the Cornerstone for AGI
Explicit memory modeled on the hippocampus is the cornerstone needed to advance LLMs to AGI because their implicit statistical learning cannot produce higher cognitive functions.
-
From Pixels to Prompts: Vision-Language Models
An explanatory book that supplies a clear mental map and intuition for how Vision-Language Models combine vision and language capabilities.
- IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures