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.
269
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.
LLM-as-an-Investigator improves diagnostic accuracy over direct prompting by using an evidence-first protocol of hypothesis generation, clarification questions, and iterative probability updates in technical problem solving.
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.
citing papers explorer
-
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
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.
-
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
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: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
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 Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
-
ORPO: Monolithic Preference Optimization without Reference Model
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: Compiling Declarative Language Model Calls into Self-Improving Pipelines
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: Interactive Simulacra of Human Behavior
Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.
-
Discovering Latent Knowledge in Language Models Without Supervision
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.
-
Code as Policies: Language Model Programs for Embodied Control
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.
-
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.
-
LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis
LLM-as-an-Investigator improves diagnostic accuracy over direct prompting by using an evidence-first protocol of hypothesis generation, clarification questions, and iterative probability updates in technical problem solving.
-
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.
-
On the Geometry of On-Policy Distillation
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.
-
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).
-
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
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: 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.
-
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
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-Testing Process Reward Models Before They Become Load-Bearing
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.
-
Bounded Behavioral Indistinguishability for Black-Box LLM Distillation
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.
-
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.
-
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
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: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
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.
-
Large Language Model Selection with Limited Annotations
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: Reinforcement Learning over Predictive Distributions for LLM Regression
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.
-
Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
The paper defines accidental meltdowns as unsafe agent behavior triggered by benign errors and reports that such meltdowns occur in 64.7% of evaluated rollouts across GPT, Grok, and Gemini agents.
-
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.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.
-
Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics
LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.
-
Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
Optimistic bilevel optimization with manifold lower-level minimizers is differentiable if the optimistic selection is unique, yielding a pseudoinverse hyper-gradient and a convergent HG-MS algorithm whose rate depends on intrinsic manifold dimension.
-
Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
Pretrained language models are used as energy functions for Glauber dynamics in discrete text diffusion, improving generation quality over prior diffusion LMs and matching autoregressive models on benchmarks and reasoning tasks.
-
ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming
ContextualJailbreak uses evolutionary search over simulated primed dialogues with novel mutations to reach 90-100% attack success on open LLMs and transfers to some closed frontier models at 15-90% rates.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
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.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
Latent Space Probing for Adult Content Detection in Video Generative Models
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
-
Rates of forgetting for the sequentially Markov coalescent
SMC forgets its initial condition geometrically in the jump chain and as 1/ℓ in continuous genetic distance, justifying independent-locus approximations.
-
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.
-
Discrete Tilt Matching
Discrete Tilt Matching recasts dLLM fine-tuning as state-level matching of tilted local unmasking posteriors, producing a stable weighted cross-entropy loss that improves Sudoku and Countdown performance when applied to LLaDA-8B-Instruct.
-
S-GRPO: Unified Post-Training for Large Vision-Language Models
S-GRPO unifies SFT and RL for LVLMs via conditional ground-truth injection that supplies a maximal-reward anchor when group exploration fails completely.
-
Reinforcement Learning via Value Gradient Flow
VGF solves behavior-regularized RL by transporting particles from a reference distribution to the value-induced optimal policy via discrete value-guided gradient flow.
-
Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
-
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
Agreeableness in AI personas reliably predicts sycophantic behavior in 9 of 13 tested language models.
-
SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation
SPASM introduces a stability-first framework with Egocentric Context Projection to maintain consistent personas and eliminate echoing in multi-turn LLM agent dialogues.
-
MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security
MCP-DPT creates a defense-placement taxonomy that organizes MCP threats and defenses across six architectural layers, revealing mostly tool-centric protections and gaps at orchestration, transport, and supply-chain layers.
-
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.
-
STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning
STEER represents videos as time-ordered event schemas and uses Pareto-Frontier guided Advantage Balancing in RL to train a 4B model that matches 7B baselines on video tasks with half the frames.
-
Alignment midtraining for animals
Midtraining on 3000 synthetic animal compassion documents raises compassionate reasoning scores to 77% on ANIMA benchmark versus 40% for instruction tuning, with generalization to human compassion but degradation after additional tuning.
-
Fast Single Nitrogen-Vacancy Center Ramsey Characterization using a Physics-Informed Neural Network
NVRNet uses pretrained simulation-based U-Nets with attention and parameter-efficient adapters, followed by a transformer estimator, to reconstruct clean Ramsey waveforms and infer hyperfine parameters from minimal-sweep experimental data, achieving 0.44-0.67x noise reduction and 0.10-0.19 FFT error