GCRL and MISL are unified as control maximization, with three inequivalent GCRL formulations each matched to a MISL objective via bounds on goal-sensitivity.
super hub Mixed citations
Finetuned Language Models Are Zero-Shot Learners
Mixed citation behavior. Most common role is background (68%).
138
Pith papers citing it
Background
68% of classified citations
abstract
This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially improves zero-shot performance on unseen tasks. We take a 137B parameter pretrained language model and instruction-tune it on over 60 NLP tasks verbalized via natural language instruction templates. We evaluate this instruction-tuned model, which we call FLAN, on unseen task types. FLAN substantially improves the performance of its unmodified counterpart and surpasses zero-shot 175B GPT-3 on 20 of 25 tasks that we evaluate. FLAN even outperforms few-shot GPT-3 by a large margin on ANLI, RTE, BoolQ, AI2-ARC, OpenbookQA, and StoryCloze. Ablation studies reveal that number of finetuning datasets, model scale, and natural language instructions are key to the success of instruction tuning.
hub tools
citation-role summary
background 33
other 5
dataset 3
method 3
citation-polarity summary
claims ledger
- abstract This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially improves zero-shot performance on unseen tasks. We take a 137B parameter pretrained language model and instruction-tune it on over 60 NLP tasks verbalized via natural language instruction templates. We evaluate this instruction-tuned model, which we call FLAN, on unseen task types. FLAN substantially improves the performance of its unmodified counterpart and sur
authors
co-cited works
representative citing papers
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.
Language models can automatically generate high-quality evaluation datasets that reveal new cases of inverse scaling, sycophancy, and concerning goal-seeking behaviors, including some worsened by RLHF.
Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.
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.
PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.
DRAPE generates query-image conditioned prompts on the fly for multimodal continual instruction tuning and reports SOTA results on MCIT benchmarks.
Stealth Pretraining Seeding plants persistent unsafe behaviors in LLMs via diffuse poisoned web content that activates on precise triggers and evades standard evaluation.
Single-agent systems with tools provide the optimal performance-efficiency trade-off for small language models, outperforming base models and multi-agent setups.
KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
MNAFT identifies language-agnostic and language-specific neurons via activation analysis and selectively fine-tunes only relevant ones in MLLMs to close the modality gap and outperform full fine-tuning and other methods on image translation benchmarks.
ProtoCycle improves text-guided protein design by coupling an LLM planner with tool feedback and reflection to achieve better language alignment and foldability than direct generation.
LLMAR applies LLM reasoning with a self-correction reflection loop to generate semantic user motives for tuning-free recommendations, showing up to 54.6% nDCG@10 gains on a sparse industrial dataset over trained baselines.
Users treat human delegation for long tasks as a flexible compass but AI delegation as rigid railway tracks due to perceived AI limitations in inference and judgment.
LLM agents outperform humans in romance-baiting scams, eliciting greater trust and 46% compliance versus 18%, with 0% detection by safety filters and 87% of scam tasks automatable.
Popular LLM activation steering methods are shown to act as proportional controllers; a PID steering framework is proposed that improves robustness and outperforms baselines in experiments across model families.
TokenBuncher constrains response entropy via entropy-as-reward RL and a Token Noiser to stop harmful RL fine-tuning while keeping benign performance intact.
The paper offers a comprehensive survey and proposes a new taxonomy for continual learning strategies in VLMs and MLLMs to combat catastrophic forgetting beyond traditional methods.
MetaLint uses meta-learning to let models generalize from easy synthetic linting data to hard human-curated best practices, yielding large F-score gains on a new PEP-inspired benchmark.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
C-Pack releases a new Chinese embedding benchmark, large training dataset, and optimized models that outperform priors by up to 10% on C-MTEB while also delivering English SOTA results.
QLoRA finetunes 4-bit quantized LLMs via LoRA adapters to match full-precision performance while using far less memory, enabling 65B-scale training on single GPUs and producing Guanaco models near ChatGPT level.
citing papers explorer
-
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.
-
Discovering Language Model Behaviors with Model-Written Evaluations
Language models can automatically generate high-quality evaluation datasets that reveal new cases of inverse scaling, sycophancy, and concerning goal-seeking behaviors, including some worsened by RLHF.
-
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.
-
PAL: Program-aided Language Models
PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.
-
Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms
Single-agent systems with tools provide the optimal performance-efficiency trade-off for small language models, outperforming base models and multi-agent setups.
-
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
-
MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation
MNAFT identifies language-agnostic and language-specific neurons via activation analysis and selectively fine-tunes only relevant ones in MLLMs to close the modality gap and outperform full fine-tuning and other methods on image translation benchmarks.
-
Self-Rewarding Language Models
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
-
C-Pack: Packed Resources For General Chinese Embeddings
C-Pack releases a new Chinese embedding benchmark, large training dataset, and optimized models that outperform priors by up to 10% on C-MTEB while also delivering English SOTA results.
-
WizardLM: Empowering large pre-trained language models to follow complex instructions
WizardLM uses LLM-driven iterative rewriting to generate complex instruction data and fine-tunes LLaMA to reach over 90% of ChatGPT capacity on 17 of 29 evaluated skills.
-
OPT: Open Pre-trained Transformer Language Models
OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.
-
Fine-Tuning Improves Information Conveyance in Language Models
Fine-tuning reorganizes uncertainty in LLMs into more efficient information conveyance, as shown by stronger length-entropy correlations and a tripling of entropy-semantic diversity links after controls.
-
Hypergraph as Language
Hyper-Align is a hypergraph-native framework that serializes high-order relations into LLM-compatible tokens via HIDT-O templates and a HIP projector, outperforming graph-centric methods on HyperAlign-Bench.
-
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
-
x1: Learning to Think Adaptively Across Languages and Cultures
x1 models adaptively select an advantageous language for reasoning per instance, yielding gains on multilingual math and cultural tasks while showing that scaling does not erase culture-language advantages.
-
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
RLBFF extracts binary principles from human feedback to train reward models that outperform Bradley-Terry models on RM-Bench and JudgeBench and enable customizable inference-time focus for LLM alignment.
-
Step-Audio 2 Technical Report
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
-
MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts
MolReFlect introduces a teacher-student framework that automatically creates fine-grained molecule-text alignments to achieve SOTA results on molecule-caption translation.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
MiniCPM 1.2B and 2.4B models reach parity with 7B-13B LLMs via model wind-tunnel scaling and a WSD scheduler that yields a higher optimal data-to-model ratio than Chinchilla scaling.
-
Steering Llama 2 via Contrastive Activation Addition
Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.
-
The Falcon Series of Open Language Models
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
-
Llemma: An Open Language Model For Mathematics
Continued pretraining of Code Llama on Proof-Pile-2 yields Llemma, an open math-specialized LLM that beats known open base models on MATH and supports tool use plus formal proving out of the box.
-
Simple synthetic data reduces sycophancy in large language models
Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.
-
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Pre-training loss predicts LLM math reasoning better than parameter count; rejection sampling fine-tuning with diverse paths raises LLaMA-7B accuracy on GSM8K from 35.9% with SFT to 49.3%.
-
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
GPT-4 as an LLM judge achieves over 80% agreement with human preferences on MT-Bench and Chatbot Arena, matching human agreement levels and providing a scalable evaluation method.
-
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
AWQ quantizes LLM weights to low bits by scaling salient channels based on activation statistics, outperforming prior methods on language, coding, math, and multi-modal benchmarks.
-
Scaling Data-Constrained Language Models
Repeating training data up to 4 epochs yields negligible loss increase versus unique data for fixed compute, and a new scaling law accounts for the decaying value of repeated tokens and excess parameters.
-
PandaGPT: One Model To Instruction-Follow Them All
A single model trained only on image-text pairs gains instruction-following ability across images, video, and audio by routing all modalities through ImageBind's shared embedding space into Vicuna.
-
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.
-
Towards Expert-Level Medical Question Answering with Large Language Models
Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.
-
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
-
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.
-
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
GPT-NeoX-20B is a publicly released 20B parameter autoregressive language model trained on the Pile that shows strong gains in five-shot reasoning over similarly sized prior models.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
-
Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study
Tokenizer fertility varies 1.6x across models on Ukrainian legal text, Qwen uses 60% more tokens than Llama-family models, zero-shot outperforms few-shot by up to 26 points, and pre-war classifiers lose 27.9 points on invasion-era decisions.
-
Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs
EngGPT2MoE-16B-A3B matches or exceeds other Italian open-source LLMs on most international benchmarks while remaining competitive on ITALIC, though it trails some top international models.
-
Why Expert Alignment Is Hard: Evidence from Subjective Evaluation
Expert alignment in subjective LLM evaluations is difficult because expert judgments are heterogeneous, partly tacit, dimension-dependent, and temporally unstable.
-
Understanding the Prompt Sensitivity
LLMs disperse meaning-preserving prompts internally instead of clustering them, which produces an excessively high upper bound on output log-probability differences via Taylor expansion and Cauchy-Schwarz.
-
Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts
Mainstream conversational models show escalating affective misalignments and ethical guidance failures during staged emotional trajectories, organized into a taxonomy of interactional breakdowns.
-
Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception
LLM agents exhibit temporal blindness, achieving no better than 65% normalized alignment with human preferences on tool-use decisions across time-sensitive scenarios in the new TicToc dataset.
-
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.
-
Quantifying Geospatial in the Common Crawl Corpus
Analysis estimates 18.7% of Common Crawl documents contain geospatial information like coordinates and addresses, with little difference by language.
-
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Empirical tests show LLMs from 1B to 7B parameters exhibit catastrophic forgetting during continual instruction tuning, with forgetting severity increasing with scale and decoder-only models retaining more than encoder-decoder models.
-
Galactica: A Large Language Model for Science
Galactica, a science-specialized LLM, reports higher scores than GPT-3, Chinchilla, and PaLM on LaTeX knowledge, mathematical reasoning, and medical QA benchmarks while outperforming general models on BIG-bench.
-
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
Trained the largest monolithic 530B-parameter transformer language model to date and reported new state-of-the-art zero- and few-shot results on multiple NLP benchmarks.
-
Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design
Machine interpreting should shift from fidelity metrics to three design priorities—agency, grounding, and experience—drawn from interpreting studies to close the usability gap with human-mediated communication.
-
ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
A new source-grounded QA dataset for U.S. immigration law is built from official documents and used to fine-tune a 3B model, yielding a 27% mean score improvement over the base model on a held-out sample.