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.
217
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
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.
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.
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.
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.
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 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 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.
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.
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.
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.
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 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 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 largely capture sycophantic accommodation to the inferred political identity of the asker rather than any fixed model ideology.
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 on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
citing papers explorer
-
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.
-
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.
-
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.
-
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
-
The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
The Stepwise Informativeness Assumption explains the correlation between LLM entropy dynamics and reasoning correctness by positing that correct traces accumulate answer-relevant information stepwise during generation.
-
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
CapTrack shows post-training causes drift beyond facts, with instruction fine-tuning producing stronger behavioral changes than preference optimization across model families.
-
"Tab, Tab, Bug": Security Pitfalls of Next Edit Suggestions in AI-Integrated IDEs
NES systems in AI IDEs expand attack surfaces via context poisoning from imperceptible actions and global codebase retrieval, with professional developers largely unaware of the risks.
-
RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
RASFT is an adaptive SFT method that strengthens or relaxes expert imitation per problem based on on-policy rollout solvability and adds clipped reference-policy ratio to limit drift, reporting better results than standard SFT and RL on math and code benchmarks.
-
What Do People Actually Want From AI? Mapping Preference Plurality
Open-ended preference data reveals substantial plurality in what people want from AI and divergent interpretations of shared values such as truthfulness.
-
Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game
LLMs produce human-like finite bids in the St. Petersburg game but shift toward rational behavior under controlled prompt changes, indicating surface-level outcome resemblance without mechanism-level alignment.
-
Annealed Softmax Greedy in Many-Armed Bayesian Bandits
Annealed softmax greedy achieves Õ(m + T/m) Bayes regret (Õ(√T) at m=Θ(√T)) in many-armed Bayesian Bernoulli bandits under linear upper-tail prior condition, matching empirical-mean greedy.
-
Understanding Goal Generalisation in Sequential Reinforcement Learning
Empirical analysis of over 100 sequential RL training pipelines across 250+ OOD environments finds salient features drive generalization and early goals persist, with latent policy gradients simulating latent variable evolution to predict OOD behavior from training history.
-
What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA
Controlled study shows mixed training curricula improve aggregate F1 on memory QA benchmarks while out-of-domain data transfers targeted skills like temporal reasoning, with per-question-type effects exceeding aggregate differences.
-
When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
Position-Weighted On-Policy Self-Distillation (PW-OPSD) weights later tokens more heavily after a diagnostic shows position predicts teacher reliability better than entropy, yielding +1.0 and +1.1 Avg@12 gains on AIME 2024/2025.
-
TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.
-
Reinforcing Human Behavior Simulation via Verbal Feedback
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark 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.
-
Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
DG-Hard uses Donoho-Gavish hard thresholding on the fine-tuning weight delta to separate task-aligned signal from noise-like residual, recovering damaged capabilities while preserving target-task gains.
-
EmbGen: Teaching with Reassembled Corpora
EmbGen creates synthetic QA data by entity decomposition, embedding-based reassembly into clusters, and multi-level sampling with cluster-specific prompts, yielding up to 88.9% higher Binary Accuracy than baselines on heterogeneous datasets under fixed token budgets.
-
Towards Human-Level Book-Writing Capability
A prompt-to-book training framework that derives hierarchical summaries from public-domain novels and inverts them to supervise long-context models toward human literary prose instead of assistant-style output.
-
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
ActFocus resolves the action bottleneck in agentic RL by reweighting token gradients toward action tokens using observed reward variance and an energy-based uncertainty term, outperforming PPO and GRPO by up to 65 percentage points.
-
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
Early mixing of post-training data into pretraining improves retention of acquired capabilities after subsequent fine-tuning in language models.
-
Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
A new RL objective adapts trust-region and off-policy handling automatically via normalized effective sample size of batch policy ratios, matching tuned baselines without new hyperparameters.
-
Rotation-Preserving Supervised Fine-Tuning
RPSFT improves the in-domain versus out-of-domain performance trade-off during LLM supervised fine-tuning by penalizing rotations in pretrained singular subspaces as a proxy for loss-sensitive directions.